Search

Current methods for initializing state space model (SSM) parameters primarily rely on the HiPPO framework \citep{gu2023how}, which is based on online function approximation with the SSM kernel basis. However, the HiPPO framework does not explicitly account for the effects of the temporal structures of input sequences on the optimization of SSMs. In this paper, we take a further step to investigate the roles of SSM initialization schemes by considering the autocorrelation of input sequences. Specifically, we: (1) rigorously characterize the dependency of the SSM timescale on sequence length based on sequence autocorrelation; (2) find that with a proper timescale, allowing a zero real part for the eigenvalues of the SSM state matrix mitigates the curse of memory while still maintaining stability at initialization; (3) show that the imaginary part of the eigenvalues of the SSM state matrix determines the conditioning of SSM optimization problems, and uncover an approximation-estimation tradeoff when training SSMs with a specific class of target functions.

Macroscopic observables of a system are of keen interest in real applications such as the design of novel materials. Current methods rely on microscopic trajectory simulations, where the forces on all microscopic coordinates need to be computed or measured. However, this can be computationally prohibitive for realistic systems. In this paper, we propose a method to learn macroscopic dynamics requiring only force computations on a subset of the microscopic coordinates. Our method relies on a sparsity assumption: the force on each microscopic coordinate relies only on a small number of other coordinates. The main idea of our approach is to map the training procedure on the macroscopic coordinates back to the microscopic coordinates, on which partial force computations can be used as stochastic estimation to update model parameters. We provide a theoretical justification of this under suitable conditions. We demonstrate the accuracy, force computation efficiency, and robustness of our method on learning macroscopic closure models from a variety of microscopic systems, including those modeled by partial differential equations or molecular dynamics simulations.

We introduce a Model Predictive Control (MPC) framework for training deep neural networks, systematically unifying the Back-Propagation (BP) and Forward-Forward (FF) algorithms. At the same time, it gives rise to a range of intermediate training algorithms with varying look-forward horizons, leading to a performance-efficiency trade-off. We perform a precise analysis of this trade-off on a deep linear network, where the qualitative conclusions carry over to general networks. Based on our analysis, we propose a principled method to choose the optimization horizon based on given objectives and model specifications. Numerical results on various models and tasks demonstrate the versatility of our method.

Scientific computing is an essential tool for scientific discovery and engineering design, and its computational cost is always a main concern in practice. To accelerate scientific computing, it is a promising approach to use machine learning (especially meta-learning) techniques for selecting hyperparameters of traditional numerical methods. There have been numerous proposals to this direction, but many of them require automatic-differentiable numerical methods. However, in reality, many practical applications still depend on well-established but non-automatic-differentiable legacy codes, which prevents practitioners from applying the state-of-the-art research to their own problems. To resolve this problem, we propose a non-intrusive methodology with a novel gradient estimation technique to combine machine learning and legacy numerical codes without any modification. We theoretically and numerically show the advantage of the proposed method over other baselines and present applications of accelerating established non-automatic-differentiable numerical solvers implemented in PETSc, a widely used open-source numerical software library.

A State Space Model (SSM) is a foundation model in time series analysis, which has recently been shown as an alternative to transformers in sequence modeling. In this paper, we theoretically study the generalization of SSMs and propose improvements to training algorithms based on the generalization results. Specifically, we give a \textit{data-dependent} generalization bound for SSMs, showing an interplay between the SSM parameters and the temporal dependencies of the training sequences. Leveraging the generalization bound, we (1) set up a scaling rule for model initialization based on the proposed generalization measure, which significantly improves the robustness of the output value scales on SSMs to different temporal patterns in the sequence data; (2) introduce a new regularization method for training SSMs to enhance the generalization performance. Numerical results are conducted to validate our results.

Despite the effectiveness of deep neural networks in numerous natural language processing applications, recent findings have exposed the vulnerability of these language models when minor perturbations are introduced. While appearing semantically indistinguishable to humans, these perturbations can significantly reduce the performance of well-trained language models, raising concerns about the reliability of deploying them in safe-critical situations. In this work, we construct a computationally efficient self-healing process to correct undesired model behavior during online inference when perturbations are applied to input data. This is formulated as a trajectory optimization problem in which the internal states of the neural network layers are automatically corrected using a PID (Proportional-Integral-Derivative) control mechanism. The P controller targets immediate state adjustments, while the I and D controllers consider past states and future dynamical trends, respectively. We leverage the geometrical properties of the training data to design effective linear PID controllers. This approach reduces the computational cost to that of using just the P controller, instead of the full PID control. Further, we introduce an analytical method for approximating the optimal control solutions, enhancing the real-time inference capabilities of this controlled system. Moreover, we conduct a theoretical error analysis of the analytic solution in a simplified setting. The proposed PID control-based self-healing is a low cost framework that improves the robustness of pre-trained large language models, whether standard or robustly trained, against a wide range of perturbations. A detailed implementation can be found in:https://github.com/zhuotongchen/PID-Control-Based-Self-Healing-to-Improve-the-Robustness-of-Large-Language-Models., Comment: Transactions on Machine Learning Research

Learning unknown stochastic differential equations (SDEs) from observed data is a significant and challenging task with applications in various fields. Current approaches often use neural networks to represent drift and diffusion functions, and construct likelihood-based loss by approximating the transition density to train these networks. However, these methods often rely on one-step stochastic numerical schemes, necessitating data with sufficiently high time resolution. In this paper, we introduce novel approximations to the transition density of the parameterized SDE: a Gaussian density approximation inspired by the random perturbation theory of dynamical systems, and its extension, the dynamical Gaussian mixture approximation (DynGMA). Benefiting from the robust density approximation, our method exhibits superior accuracy compared to baseline methods in learning the fully unknown drift and diffusion functions and computing the invariant distribution from trajectory data. And it is capable of handling trajectory data with low time resolution and variable, even uncontrollable, time step sizes, such as data generated from Gillespie's stochastic simulations. We then conduct several experiments across various scenarios to verify the advantages and robustness of the proposed method.

In this paper, we investigate the long-term memory learning capabilities of state-space models (SSMs) from the perspective of parameterization. We prove that state-space models without any reparameterization exhibit a memory limitation similar to that of traditional RNNs: the target relationships that can be stably approximated by state-space models must have an exponential decaying memory. Our analysis identifies this "curse of memory" as a result of the recurrent weights converging to a stability boundary, suggesting that a reparameterization technique can be effective. To this end, we introduce a class of reparameterization techniques for SSMs that effectively lift its memory limitations. Besides improving approximation capabilities, we further illustrate that a principled choice of reparameterization scheme can also enhance optimization stability. We validate our findings using synthetic datasets, language models and image classifications., Comment: 28 pages, 7 figures, ICML 2024

The performance of state-of-the-art machine learning models often deteriorates when testing on demographics that are under-represented in the training dataset. This problem has predominately been studied in a supervised learning setting where the data distribution is static. However, real-world applications often involve distribution shifts caused by the deployed models. For instance, the performance disparity against monitory users can lead to a high customer churn rate, thus the available data provided by active users are skewed due to the lack of minority users. This feedback effect further exacerbates the disparity among different demographic groups in future steps. To address this issue, we propose asymptotically fair participation as a condition to maintain long-term model performance over all demographic groups. In this work, we aim to address the problem of achieving asymptotically fair participation via optimal control formulation. Moreover, we design a surrogate retention system based on existing literature on evolutionary population dynamics to approximate the dynamics of distribution shifts on active user counts, from which the objective of achieving asymptotically fair participation is formulated as an optimal control problem, and the control variables are considered as the model parameters. We apply an efficient implementation of Pontryagin's maximum principle to estimate the optimal control solution. To evaluate the effectiveness of the proposed method, we design a generic simulation environment that simulates the population dynamics of the feedback effect between user retention and model performance. When we deploy the resulting models to the simulation environment, the optimal control solution accounts for long-term planning and leads to superior performance compared with existing baseline methods., Comment: 34 pages

In data-driven modelling of complex dynamic processes, it is often desirable to combine different classes of models to enhance performance. Examples include coupled models of different fidelities, or hybrid models based on physical knowledge and data-driven strategies. A key limitation of the broad adoption of model combination in applications is intrusiveness: training combined models typically requires significant modifications to the learning algorithm implementations, which may often be already well-developed and optimized for individual model spaces. In this work, we propose an iterative, non-intrusive methodology to combine two model spaces to learn dynamics from data. We show that this can be understood, at least in the linear setting, as finding the optimal solution in the direct sum of the two hypothesis spaces, while leveraging only the projection operators in each individual space. Hence, the proposed algorithm can be viewed as iterative projections, for which we can obtain estimates on its convergence properties. To highlight the extensive applicability of our framework, we conduct numerical experiments in various problem settings, with particular emphasis on various hybrid models based on the Koopman operator approach., Comment: 43 pages, 11 figures

We present an approach to construct approximate Koopman-type decompositions for dynamical systems depending on static or time-varying parameters. Our method simultaneously constructs an invariant subspace and a parametric family of projected Koopman operators acting on this subspace. We parametrize both the projected Koopman operator family and the dictionary that spans the invariant subspace by neural networks and jointly train them with trajectory data. We show theoretically the validity of our approach, and demonstrate via numerical experiments that it exhibits significant improvements over existing methods in solving prediction problems, especially those with large state or parameter dimensions, and those possessing strongly non-linear dynamics. Moreover, our method enables data-driven solution of optimal control problems involving non-linear dynamics, with interesting implications on controllability.

We investigate the expressive power of deep residual neural networks idealized as continuous dynamical systems through control theory. Specifically, we consider two properties that arise from supervised learning, namely universal interpolation - the ability to match arbitrary input and target training samples - and the closely related notion of universal approximation - the ability to approximate input-target functional relationships via flow maps. Under the assumption of affine invariance of the control family, we give a characterisation of universal interpolation, showing that it holds for essentially any architecture with non-linearity. Furthermore, we elucidate the relationship between universal interpolation and universal approximation in the context of general control systems, showing that the two properties cannot be deduced from each other. At the same time, we identify conditions on the control family and the target function that ensures the equivalence of the two notions.

One of the most exciting applications of artificial intelligence (AI) is automated scientific discovery based on previously amassed data, coupled with restrictions provided by known physical principles, including symmetries and conservation laws. Such automated hypothesis creation and verification can assist scientists in studying complex phenomena, where traditional physical intuition may fail. Here we develop a platform based on a generalized Onsager principle to learn macroscopic dynamical descriptions of arbitrary stochastic dissipative systems directly from observations of their microscopic trajectories. Our method simultaneously constructs reduced thermodynamic coordinates and interprets the dynamics on these coordinates. We demonstrate its effectiveness by studying theoretically and validating experimentally the stretching of long polymer chains in an externally applied field. Specifically, we learn three interpretable thermodynamic coordinates and build a dynamical landscape of polymer stretching, including the identification of stable and transition states and the control of the stretching rate. Our general methodology can be used to address a wide range of scientific and technological applications., Comment: Fix figure visibility issue

We prove an inverse approximation theorem for the approximation of nonlinear sequence-to-sequence relationships using recurrent neural networks (RNNs). This is a so-called Bernstein-type result in approximation theory, which deduces properties of a target function under the assumption that it can be effectively approximated by a hypothesis space. In particular, we show that nonlinear sequence relationships that can be stably approximated by nonlinear RNNs must have an exponential decaying memory structure - a notion that can be made precise. This extends the previously identified curse of memory in linear RNNs into the general nonlinear setting, and quantifies the essential limitations of the RNN architecture for learning sequential relationships with long-term memory. Based on the analysis, we propose a principled reparameterization method to overcome the limitations. Our theoretical results are confirmed by numerical experiments. The code has been released in https://github.com/radarFudan/Curse-of-memory

We present a theoretical analysis of the approximation properties of convolutional architectures when applied to the modeling of temporal sequences. Specifically, we prove an approximation rate estimate (Jackson-type result) and an inverse approximation theorem (Bernstein-type result), which together provide a comprehensive characterization of the types of sequential relationships that can be efficiently captured by a temporal convolutional architecture. The rate estimate improves upon a previous result via the introduction of a refined complexity measure, whereas the inverse approximation theorem is new.

The Transformer architecture is widely applied in sequence modeling applications, yet the theoretical understanding of its working principles remains limited. In this work, we investigate the approximation rate for single-layer Transformers with one head. We consider a class of non-linear relationships and identify a novel notion of complexity measures to establish an explicit Jackson-type approximation rate estimate for the Transformer. This rate reveals the structural properties of the Transformer and suggests the types of sequential relationships it is best suited for approximating. In particular, the results on approximation rates enable us to concretely analyze the differences between the Transformer and classical sequence modeling methods, such as recurrent neural networks.

We survey current developments in the approximation theory of sequence modelling in machine learning. Particular emphasis is placed on classifying existing results for various model architectures through the lens of classical approximation paradigms, and the insights one can gain from these results. We also outline some future research directions towards building a theory of sequence modelling.

We study the approximation of shift-invariant or equivariant functions by deep fully convolutional networks from the dynamical systems perspective. We prove that deep residual fully convolutional networks and their continuous-layer counterpart can achieve universal approximation of these symmetric functions at constant channel width. Moreover, we show that the same can be achieved by non-residual variants with at least 2 channels in each layer and convolutional kernel size of at least 2. In addition, we show that these requirements are necessary, in the sense that networks with fewer channels or smaller kernels fail to be universal approximators., Comment: 25 pages

Meta-learning of numerical algorithms for a given task consists of the data-driven identification and adaptation of an algorithmic structure and the associated hyperparameters. To limit the complexity of the meta-learning problem, neural architectures with a certain inductive bias towards favorable algorithmic structures can, and should, be used. We generalize our previously introduced Runge-Kutta neural network to a recursively recurrent neural network (R2N2) superstructure for the design of customized iterative algorithms. In contrast to off-the-shelf deep learning approaches, it features a distinct division into modules for generation of information and for the subsequent assembly of this information towards a solution. Local information in the form of a subspace is generated by subordinate, inner, iterations of recurrent function evaluations starting at the current outer iterate. The update to the next outer iterate is computed as a linear combination of these evaluations, reducing the residual in this space, and constitutes the output of the network. We demonstrate that regular training of the weight parameters inside the proposed superstructure on input/output data of various computational problem classes yields iterations similar to Krylov solvers for linear equation systems, Newton-Krylov solvers for nonlinear equation systems, and Runge-Kutta integrators for ordinary differential equations. Due to its modularity, the superstructure can be readily extended with functionalities needed to represent more general classes of iterative algorithms traditionally based on Taylor series expansions., Comment: manuscript (22 pages, 9 figures), supporting information (11 pages, 9 figures)

Needle-in-a-Haystack problems exist across a wide range of applications including rare disease prediction, ecological resource management, fraud detection, and material property optimization. A Needle-in-a-Haystack problem arises when there is an extreme imbalance of optimum conditions relative to the size of the dataset. For example, only $0.82\%$ out of $146$k total materials in the open-access Materials Project database have a negative Poisson's ratio. However, current state-of-the-art optimization algorithms are not designed with the capabilities to find solutions to these challenging multidimensional Needle-in-a-Haystack problems, resulting in slow convergence to a global optimum or pigeonholing into a local minimum. In this paper, we present a Zooming Memory-Based Initialization algorithm, entitled ZoMBI. ZoMBI actively extracts knowledge from the previously best-performing evaluated experiments to iteratively zoom in the sampling search bounds towards the global optimum "needle" and then prunes the memory of low-performing historical experiments to accelerate compute times by reducing the algorithm time complexity from $O(n^3)$ to $O(\phi^3)$ for $\phi$ forward experiments per activation, which trends to a constant $O(1)$ over several activations. Additionally, ZoMBI implements two custom adaptive acquisition functions to further guide the sampling of new experiments toward the global optimum. We validate the algorithm's optimization performance on three real-world datasets exhibiting Needle-in-a-Haystack and further stress-test the algorithm's performance on an additional 174 analytical datasets. The ZoMBI algorithm demonstrates compute time speed-ups of 400x compared to traditional Bayesian optimization as well as efficiently discovering optima in under 100 experiments that are up to 3x more highly optimized than those discovered by similar methods MiP-EGO, TuRBO, and HEBO., Comment: Paper 16 pages; SI 6 pages

We study the approximation of functions which are invariant with respect to certain permutations of the input indices using flow maps of dynamical systems. Such invariant functions includes the much studied translation-invariant ones involving image tasks, but also encompasses many permutation-invariant functions that finds emerging applications in science and engineering. We prove sufficient conditions for universal approximation of these functions by a controlled equivariant dynamical system, which can be viewed as a general abstraction of deep residual networks with symmetry constraints. These results not only imply the universal approximation for a variety of commonly employed neural network architectures for symmetric function approximation, but also guide the design of architectures with approximation guarantees for applications involving new symmetry requirements.

Despite the wide applications of neural networks, there have been increasing concerns about their vulnerability issue. While numerous attack and defense techniques have been developed, this work investigates the robustness issue from a new angle: can we design a self-healing neural network that can automatically detect and fix the vulnerability issue by itself? A typical self-healing mechanism is the immune system of a human body. This biology-inspired idea has been used in many engineering designs but is rarely investigated in deep learning. This paper considers the post-training self-healing of a neural network, and proposes a closed-loop control formulation to automatically detect and fix the errors caused by various attacks or perturbations. We provide a margin-based analysis to explain how this formulation can improve the robustness of a classifier. To speed up the inference of the proposed self-healing network, we solve the control problem via improving the Pontryagin Maximum Principle-based solver. Lastly, we present an error estimation of the proposed framework for neural networks with nonlinear activation functions. We validate the performance on several network architectures against various perturbations. Since the self-healing method does not need a-priori information about data perturbations/attacks, it can handle a broad class of unforeseen perturbations., Comment: 48 pages, 5 figures

Iterative methods are ubiquitous in large-scale scientific computing applications, and a number of approaches based on meta-learning have been recently proposed to accelerate them. However, a systematic study of these approaches and how they differ from meta-learning is lacking. In this paper, we propose a framework to analyze such learning-based acceleration approaches, where one can immediately identify a departure from classical meta-learning. We show that this departure may lead to arbitrary deterioration of model performance. Based on our analysis, we introduce a novel training method for learning-based acceleration of iterative methods. Furthermore, we theoretically prove that the proposed method improves upon the existing methods, and demonstrate its significant advantage and versatility through various numerical applications.

Transfer learning increasingly becomes an important tool in handling data scarcity often encountered in machine learning. In the application of high-throughput thickness as a downstream process of the high-throughput optimization of optoelectronic thin films with autonomous workflows, data scarcity occurs especially for new materials. To achieve high-throughput thickness characterization, we propose a machine learning model called thicknessML that predicts thickness from UV-Vis spectrophotometry input and an overarching transfer learning workflow. We demonstrate the transfer learning workflow from generic source domain of generic band-gapped materials to specific target domain of perovskite materials, where the target domain data only come from limited number (18) of refractive indices from literature. The target domain can be easily extended to other material classes with a few literature data. Defining thickness prediction accuracy to be within-10% deviation, thicknessML achieves 92.2% (with a deviation of 3.6%) accuracy with transfer learning compared to 81.8% (with a deviation of 3.6%) 11.7% without (lower mean and larger standard deviation). Experimental validation on six deposited perovskite films also corroborates the efficacy of the proposed workflow by yielding a 10.5% mean absolute percentage error (MAPE).

Conventional wisdom of materials modelling stipulates that both chemical composition and crystal structure are integral in the prediction of physical properties. However, recent developments challenge this by reporting accurate property-prediction machine learning (ML) frameworks using composition alone without knowledge of the local atomic environments or long-range order. To probe this behavior, we conduct a systematic comparison of supervised ML models built on composition only vs. composition plus structure features. Similar performance for property prediction is found using both models for compounds close to the thermodynamic convex hull. We hypothesize that composition embeds structural information of ground-state structures in support of composition-centric models for property prediction and inverse design of stable compounds., Comment: 18 pages, 8 figures

Optimization and generalization are two essential aspects of statistical machine learning. In this paper, we propose a framework to connect optimization with generalization by analyzing the generalization error based on the optimization trajectory under the gradient flow algorithm. The key ingredient of this framework is the Uniform-LGI, a property that is generally satisfied when training machine learning models. Leveraging the Uniform-LGI, we first derive convergence rates for gradient flow algorithm, then we give generalization bounds for a large class of machine learning models. We further apply our framework to three distinct machine learning models: linear regression, kernel regression, and two-layer neural networks. Through our approach, we obtain generalization estimates that match or extend previous results.

The invariant distribution, which is characterized by the stationary Fokker-Planck equation, is an important object in the study of randomly perturbed dynamical systems. Traditional numerical methods for computing the invariant distribution based on the Fokker-Planck equation, such as finite difference or finite element methods, are limited to low-dimensional systems due to the curse of dimensionality. In this work, we propose a deep learning based method to compute the generalized potential, i.e. the negative logarithm of the invariant distribution multiplied by the noise. The idea of the method is to learn a decomposition of the force field, as specified by the Fokker-Planck equation, from the trajectory data. The potential component of the decomposition gives the generalized potential. The method can deal with high-dimensional systems, possibly with partially known dynamics. Using the generalized potential also allows us to deal with systems at low temperatures, where the invariant distribution becomes singular around the metastable states. These advantages make it an efficient method to analyze invariant distributions for practical dynamical systems. The effectiveness of the proposed method is demonstrated by numerical examples.

We study the approximation properties of convolutional architectures applied to time series modelling, which can be formulated mathematically as a functional approximation problem. In the recurrent setting, recent results reveal an intricate connection between approximation efficiency and memory structures in the data generation process. In this paper, we derive parallel results for convolutional architectures, with WaveNet being a prime example. Our results reveal that in this new setting, approximation efficiency is not only characterised by memory, but also additional fine structures in the target relationship. This leads to a novel definition of spectrum-based regularity that measures the complexity of temporal relationships under the convolutional approximation scheme. These analyses provide a foundation to understand the differences between architectural choices for time series modelling and can give theoretically grounded guidance for practical applications., Comment: Published version

We study the learning of numerical algorithms for scientific computing, which combines mathematically driven, handcrafted design of general algorithm structure with a data-driven adaptation to specific classes of tasks. This represents a departure from the classical approaches in numerical analysis, which typically do not feature such learning-based adaptations. As a case study, we develop a machine learning approach that automatically learns effective solvers for initial value problems in the form of ordinary differential equations (ODEs), based on the Runge-Kutta (RK) integrator architecture. We show that we can learn high-order integrators for targeted families of differential equations without the need for computing integrator coefficients by hand. Moreover, we demonstrate that in certain cases we can obtain superior performance to classical RK methods. This can be attributed to certain properties of the ODE families being identified and exploited by the approach. Overall, this work demonstrates an effective learning-based approach to the design of algorithms for the numerical solution of differential equations. This can be readily extended to other numerical tasks.

An increasingly popular method for solving a constrained combinatorial optimisation problem is to first convert it into a quadratic unconstrained binary optimisation (QUBO) problem, and solve it using a standard QUBO solver. However, this relaxation introduces hyper-parameters that balance the objective and penalty terms for the constraints, and their chosen values significantly impact performance. Hence, tuning these parameters is an important problem. Existing generic hyper-parameter tuning methods require multiple expensive calls to a QUBO solver, making them impractical for performance critical applications when repeated solutions of similar combinatorial optimisation problems are required. In this paper, we propose the QROSS method, in which we build surrogate models of QUBO solvers via learning from solver data on a collection of instances of a problem. In this way, we are able capture the common structure of the instances and their interactions with the solver, and produce good choices of penalty parameters with fewer number of calls to the QUBO solver. We take the Traveling Salesman Problem (TSP) as a case study, where we demonstrate that our method can find better solutions with fewer calls to QUBO solver compared with conventional hyper-parameter tuning techniques. Moreover, with simple adaptation methods, QROSS is shown to generalise well to out-of-distribution datasets and different types of QUBO solvers., Comment: 17 pages

Despite their success in massive engineering applications, deep neural networks are vulnerable to various perturbations due to their black-box nature. Recent study has shown that a deep neural network can misclassify the data even if the input data is perturbed by an imperceptible amount. In this paper, we address the robustness issue of neural networks by a novel close-loop control method from the perspective of dynamic systems. Instead of modifying the parameters in a fixed neural network architecture, a close-loop control process is added to generate control signals adaptively for the perturbed or corrupted data. We connect the robustness of neural networks with optimal control using the geometrical information of underlying data to design the control objective. The detailed analysis shows how the embedding manifolds of state trajectory affect error estimation of the proposed method. Our approach can simultaneously maintain the performance on clean data and improve the robustness against many types of data perturbations. It can also further improve the performance of robustly trained neural networks against different perturbations. To the best of our knowledge, this is the first work that improves the robustness of neural networks with close-loop control., Comment: Published as a conference paper at ICLR 2021

Despite the empirical success in various domains, it has been revealed that deep neural networks are vulnerable to maliciously perturbed input data that much degrade their performance. This is known as adversarial attacks. To counter adversarial attacks, adversarial training formulated as a form of robust optimization has been demonstrated to be effective. However, conducting adversarial training brings much computational overhead compared with standard training. In order to reduce the computational cost, we propose an annealing mechanism, Amata, to reduce the overhead associated with adversarial training. The proposed Amata is provably convergent, well-motivated from the lens of optimal control theory and can be combined with existing acceleration methods to further enhance performance. It is demonstrated that on standard datasets, Amata can achieve similar or better robustness with around 1/3 to 1/2 the computational time compared with traditional methods. In addition, Amata can be incorporated into other adversarial training acceleration algorithms (e.g. YOPO, Free, Fast, and ATTA), which leads to further reduction in computational time on large-scale problems.

The quasipotential is a natural generalization of the concept of energy functions to non-equilibrium systems. In the analysis of rare events in stochastic dynamics, it plays a central role in characterizing the statistics of transition events and the likely transition paths. However, computing the quasipotential is challenging, especially in high dimensional dynamical systems where a global landscape is sought. Traditional methods based on the dynamic programming principle or path space minimization tend to suffer from the curse of dimensionality. In this paper, we propose a simple and efficient machine learning method to resolve this problem. The key idea is to learn an orthogonal decomposition of the vector field that drives the dynamics, from which one can identify the quasipotential. We demonstrate on various example systems that our method can effectively compute quasipotential landscapes without requiring spatial discretization or solving path-space optimization problems. Moreover, the method is purely data driven in the sense that only observed trajectories of the dynamics are required for the computation of the quasipotential. These properties make it a promising method to enable the general application of quasipotential analysis to dynamical systems away from equilibrium.

Combining high-throughput experiments with machine learning allows quick optimization of parameter spaces towards achieving target properties. In this study, we demonstrate that machine learning, combined with multi-labeled datasets, can additionally be used for scientific understanding and hypothesis testing. We introduce an automated flow system with high-throughput drop-casting for thin film preparation, followed by fast characterization of optical and electrical properties, with the capability to complete one cycle of learning of fully labeled ~160 samples in a single day. We combine regio-regular poly-3-hexylthiophene with various carbon nanotubes to achieve electrical conductivities as high as 1200 S/cm. Interestingly, a non-intuitive local optimum emerges when 10% of double-walled carbon nanotubes are added with long single wall carbon nanotubes, where the conductivity is seen to be as high as 700 S/cm, which we subsequently explain with high fidelity optical characterization. Employing dataset resampling strategies and graph-based regressions allows us to account for experimental cost and uncertainty estimation of correlated multi-outputs, and supports the proving of the hypothesis linking charge delocalization to electrical conductivity. We therefore present a robust machine-learning driven high-throughput experimental scheme that can be applied to optimize and understand properties of composites, or hybrid organic-inorganic materials., Comment: 10 pages, 5 figures, includes Supplementary Information

The future of mobility-as-a-Service (Maas)should embrace an integrated system of ride-hailing, street-hailing and ride-sharing with optimised intelligent vehicle routing in response to a real-time, stochastic demand pattern. We aim to optimise routing policies for a large fleet of vehicles for street-hailing services, given a stochastic demand pattern in small to medium-sized road networks. A model-based dispatch algorithm, a high performance model-free reinforcement learning based algorithm and a novel hybrid algorithm combining the benefits of both the top-down approach and the model-free reinforcement learning have been proposed to route the \emph{vacant} vehicles. We design our reinforcement learning based routing algorithm using proximal policy optimisation and combined intrinsic and extrinsic rewards to strike a balance between exploration and exploitation. Using a large-scale agent-based microscopic simulation platform to evaluate our proposed algorithms, our model-free reinforcement learning and hybrid algorithm show excellent performance on both artificial road network and community-based Singapore road network with empirical demands, and our hybrid algorithm can significantly accelerate the model-free learner in the process of learning., Comment: 24 pages, comments welcome

We study the approximation properties and optimization dynamics of recurrent neural networks (RNNs) when applied to learn input-output relationships in temporal data. We consider the simple but representative setting of using continuous-time linear RNNs to learn from data generated by linear relationships. Mathematically, the latter can be understood as a sequence of linear functionals. We prove a universal approximation theorem of such linear functionals, and characterize the approximation rate and its relation with memory. Moreover, we perform a fine-grained dynamical analysis of training linear RNNs, which further reveal the intricate interactions between memory and learning. A unifying theme uncovered is the non-trivial effect of memory, a notion that can be made precise in our framework, on approximation and optimization: when there is long term memory in the target, it takes a large number of neurons to approximate it. Moreover, the training process will suffer from slow downs. In particular, both of these effects become exponentially more pronounced with memory - a phenomenon we call the "curse of memory". These analyses represent a basic step towards a concrete mathematical understanding of new phenomenon that may arise in learning temporal relationships using recurrent architectures., Comment: Updated to include the condition $\sup_n \| \boldsymbol{x}(n) \|_{\mathcal{X}} \leq 1$ in the definition of regularity, which excludes the trivial case where only the zero functional is regular. Fixed various typos and improved clarity

We propose a systematic method for learning stable and physically interpretable dynamical models using sampled trajectory data from physical processes based on a generalized Onsager principle. The learned dynamics are autonomous ordinary differential equations parameterized by neural networks that retain clear physical structure information, such as free energy, diffusion, conservative motion and external forces. For high dimensional problems with a low dimensional slow manifold, an autoencoder with metric preserving regularization is introduced to find the low dimensional generalized coordinates on which we learn the generalized Onsager dynamics. Our method exhibits clear advantages over existing methods on benchmark problems for learning ordinary differential equations. We further apply this method to study Rayleigh-Benard convection and learn Lorenz-like low dimensional autonomous reduced order models that capture both qualitative and quantitative properties of the underlying dynamics. This forms a general approach to building reduced order models for forced dissipative systems., Comment: 29 pages, 19 figures

Realizing general inverse design could greatly accelerate the discovery of new materials with user-defined properties. However, state-of-the-art generative models tend to be limited to a specific composition or crystal structure. Herein, we present a framework capable of general inverse design (not limited to a given set of elements or crystal structures), featuring a generalized invertible representation that encodes crystals in both real and reciprocal space, and a property-structured latent space from a variational autoencoder (VAE). In three design cases, the framework generates 142 new crystals with user-defined formation energies, bandgap, thermoelectric (TE) power factor, and combinations thereof. These generated crystals, absent in the training database, are validated by first-principles calculations. The success rates (number of first-principles-validated target-satisfying crystals/number of designed crystals) ranges between 7.1% and 38.9%. These results represent a significant step toward property-driven general inverse design using generative models, although practical challenges remain when coupled with experimental synthesis.

We present the viewpoint that optimization problems encountered in machine learning can often be interpreted as minimizing a convex functional over a function space, but with a non-convex constraint set introduced by model parameterization. This observation allows us to repose such problems via a suitable relaxation as convex optimization problems in the space of distributions over the training parameters. We derive some simple relationships between the distribution-space problem and the original problem, e.g. a distribution-space solution is at least as good as a solution in the original space. Moreover, we develop a numerical algorithm based on mixture distributions to perform approximate optimization directly in distribution space. Consistency of this approximation is established and the numerical efficacy of the proposed algorithm is illustrated on simple examples. In both theory and practice, this formulation provides an alternative approach to large-scale optimization in machine learning., Comment: 26 pages, 12 figures

While current machine learning models have impressive performance over a wide range of applications, their large size and complexity render them unsuitable for tasks such as remote monitoring on edge devices with limited storage and computational power. A naive approach to resolve this on the model level is to use simpler architectures, but this sacrifices prediction accuracy and is unsuitable for monitoring applications requiring accurate detection of the onset of adverse events. In this paper, we propose an alternative solution to this problem by decomposing the predictive model as the sum of a simple function which serves as a local monitoring tool, and a complex correction term to be evaluated on the server. A sign requirement is imposed on the latter to ensure that the local monitoring function is safe, in the sense that it can effectively serve as an early warning system. Our analysis quantifies the trade-offs between model complexity and performance, and serves as a guidance for architecture design. We validate our proposed framework on a series of monitoring experiments, where we succeed at learning monitoring models with significantly reduced complexity that minimally violate the safety requirement. More broadly, our framework is useful for learning classifiers in applications where false negatives are significantly more costly compared to false positives.

We build on the dynamical systems approach to deep learning, where deep residual networks are idealized as continuous-time dynamical systems, from the approximation perspective. In particular, we establish general sufficient conditions for universal approximation using continuous-time deep residual networks, which can also be understood as approximation theories in $L^p$ using flow maps of dynamical systems. In specific cases, rates of approximation in terms of the time horizon are also established. Overall, these results reveal that composition function approximation through flow maps present a new paradigm in approximation theory and contributes to building a useful mathematical framework to investigate deep learning., Comment: Revision 1

Process optimization of photovoltaic devices is a time-intensive, trial and error endeavor, without full transparency of the underlying physics, and with user-imposed constraints that may or may not lead to a global optimum. Herein, we demonstrate that embedding physics domain knowledge into a Bayesian network enables an optimization approach that identifies the root cause(s) of underperformance with layer by-layer resolution and reveals alternative optimal process windows beyond global black-box optimization. Our Bayesian-network approach links process conditions to materials descriptors (bulk and interface properties, e.g., bulk lifetime, doping, and surface recombination) and device performance parameters (e.g., cell efficiency), using a Bayesian inference framework with an autoencoder-based surrogate device-physics model that is 100x faster than numerical solvers. With the trained surrogate model, our approach is robust and reduces significantly the time consuming experimentalist intervention, even with small numbers of fabricated samples. To demonstrate our method, we perform layer-by-layer optimization of GaAs solar cells. In a single cycle of learning, we find an improved growth temperature for the GaAs solar cells without any secondary measurements, and demonstrate a 6.5% relative AM1.5G efficiency improvement above baseline and traditional black-box optimization methods.

Distributed optimization often consists of two updating phases: local optimization and inter-node communication. Conventional approaches require working nodes to communicate with the server every one or few iterations to guarantee convergence. In this paper, we establish a completely different conclusion that each node can perform an arbitrary number of local optimization steps before communication. Moreover, we show that the more local updating can reduce the overall communication, even for an infinity number of steps where each node is free to update its local model to near-optimality before exchanging information. The extra assumption we make is that the optimal sets of local loss functions have a non-empty intersection, which is inspired by the over-paramterization phenomenon in large-scale optimization and deep learning. Our theoretical findings are confirmed by both distributed convex optimization and deep learning experiments.