Search

Equivariant neural networks have shown great success in reinforcement learning, improving sample efficiency and generalization when there is symmetry in the task. However, in many problems, only approximate symmetry is present, which makes imposing exact symmetry inappropriate. Recently, approximately equivariant networks have been proposed for supervised classification and modeling physical systems. In this work, we develop approximately equivariant algorithms in reinforcement learning (RL). We define approximately equivariant MDPs and theoretically characterize the effect of approximate equivariance on the optimal Q function. We propose novel RL architectures using relaxed group convolutions and experiment on several continuous control domains and stock trading with real financial data. Our results demonstrate that approximate equivariance matches prior work when exact symmetries are present, and outperforms them when domains exhibit approximate symmetry. As an added byproduct of these techniques, we observe increased robustness to noise at test time., Comment: Preprint

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

With the aim of studying subspaces in pointfree bitopology, we characterize extremal epimorphism in biframes and show that a smallest dense one always exists, providing an analogue of Isbell's Density Theorem. Further we study the functoriality of assigning to each biframe its lattice of subbilocales and its smallest dense subbilocale.

Many manipulation tasks require the robot to rearrange objects relative to one another. Such tasks can be described as a sequence of relative poses between parts of a set of rigid bodies. In this work, we propose MATCH POLICY, a simple but novel pipeline for solving high-precision pick and place tasks. Instead of predicting actions directly, our method registers the pick and place targets to the stored demonstrations. This transfers action inference into a point cloud registration task and enables us to realize nontrivial manipulation policies without any training. MATCH POLICY is designed to solve high-precision tasks with a key-frame setting. By leveraging the geometric interaction and the symmetries of the task, it achieves extremely high sample efficiency and generalizability to unseen configurations. We demonstrate its state-of-the-art performance across various tasks on RLBench benchmark compared with several strong baselines and test it on a real robot with six tasks., Comment: project url: https://haojhuang.github.io/match_page/

We utilize the Bruns-Lakser completion to introduce Bruns-Lakser towers of a meet-semilattice. This machinery enables us to develop various hierarchies inside the class of bounded distributive lattices, which measure $\kappa$-degrees of distributivity of bounded distributive lattices and their Dedekind-MacNeille completions. We also use Priestley duality to obtain a dual characterization of the resulting hierarchies. Among other things, this yields a natural generalization of Esakia's representation of Heyting lattices to proHeyting lattices.

We investigate a random geometric graph model introduced by Bonato and Janssen. The vertices are the points of a countable dense set $S$ in a (necessarily separable) normed vector space $X$, and each pair of points are joined independently with some fixed probability $p$ (with $0

Instabilities driven by pressure anisotropy play a critical role in modulating the energy transfer in space and astrophysical plasmas. For the first time, we simulate the evolution and saturation of the parallel proton firehose instability using a multi-fluid model without adding artificial viscosity. These simulations are performed using a 10-moment, multi-fluid model with local and gradient relaxation heat-flux closures in high-$\beta$ proton-electron plasmas. When these higher-order moments are included and pressure anisotropy is permitted to develop in all species, we find that the electrons have a significant impact on the saturation of the parallel proton firehose instability, modulating the proton pressure anisotropy as the instability saturates. Even for lower $\beta$s more relevant to heliospheric plasmas, we observe a pronounced electron energization in simulations using the gradient relaxation closure. Our results indicate that resolving the electron pressure anisotropy is important to correctly describe the behavior of multi-species plasma systems., Comment: 10 pages, 7 figures, under review in ApJ

3D Euclidean symmetry equivariant neural networks have demonstrated notable success in modeling complex physical systems. We introduce a framework for relaxed $E(3)$ graph equivariant neural networks that can learn and represent symmetry breaking within continuous groups. Building on the existing e3nn framework, we propose the use of relaxed weights to allow for controlled symmetry breaking. We show empirically that these relaxed weights learn the correct amount of symmetry breaking., Comment: Extended abstract presented at the Geometry-grounded Representation Learning and Generative Modeling Workshop (GRaM) at the 41st International Conference on Machine Learning, July 2024, Vienna, Austria

Estimating many-body effects that deviate from an independent particle approach, has long been a key research interest in condensed matter physics. Layered cuprates are prototypical systems, where electron-electron interactions are found to strongly affect the dynamics of single-particle excitations. It is however, still unclear how the electron correlations influence charge excitations, such as plasmons, which have been variously treated with either weak or strong correlation models. In this work, we demonstrate the hybridised nature of collective valence charge fluctuations leading to dispersing acoustic-like plasmons in hole-doped La$_{1.84}$Sr$_{0.16}$CuO$_{4}$ and electron-doped La$_{1.84}$Ce$_{0.16}$CuO$_{4}$ using the two-particle probe, resonant inelastic x-ray scattering. We then describe the plasmon dispersions in both systems, within both the weak mean-field Random Phase Approximation (RPA) and strong coupling $t$-$J$-$V$ models. The $t$-$J$-$V$ model, which includes the correlation effects implicitly, accurately describes the plasmon dispersions as resonant excitations outside the single-particle intra-band continuum. In comparison, a quantitative description of the plasmon dispersion in the RPA approach is obtained only upon explicit consideration of re-normalized electronic band parameters. Our comparative analysis shows that electron correlations significantly impact the low-energy plasmon excitations across the cuprate doping phase diagram, even at long wavelengths. Thus, complementary information on the evolution of electron correlations, influenced by the rich electronic phases in condensed matter systems, can be extracted through the study of two-particle charge response., Comment: 6 Figures

The QCD axion and axion-like particles are compelling candidates for galactic dark matter. Theoretically, axions can convert into photons in the presence of a strong external magnetic field, which means it is possible to search for them experimentally. One approach is to use radio telescopes with high-resolution spectrometers to look for axion-photon conversion in the magnetospheres of neutron stars. In this paper, we describe the results obtained using a novel approach where we used the Green Bank Telescope (GBT) to search for radio transients produced by collisions between neutron stars and dark matter clumps known as axion miniclusters. We used the VErsatile GBT Astronomical Spectrometer (VEGAS) and the X-band receiver (8 to 10 GHz) to observe the core of Andromeda. Our measurements are sensitive to axions with masses between 33 and 42 $\mu$eV with $\Delta$$m_a$ = 3.8$\times10^{-4}$ $\mu$eV. This paper gives a description of the search method we developed, including observation and analysis strategies. Given our analysis algorithm choices and the instrument sensitivity ($\sim$2 mJy in each spectral channel), we did not find any candidate signals greater than 5$\sigma$. We are currently implementing this search method in other spectral bands., Comment: 19 pages, 12 figures, accepted to PRD

While grasp detection is an important part of any robotic manipulation pipeline, reliable and accurate grasp detection in $SE(3)$ remains a research challenge. Many robotics applications in unstructured environments such as the home or warehouse would benefit a lot from better grasp performance. This paper proposes a novel framework for detecting $SE(3)$ grasp poses based on point cloud input. Our main contribution is to propose an $SE(3)$-equivariant model that maps each point in the cloud to a continuous grasp quality function over the 2-sphere $S^2$ using spherical harmonic basis functions. Compared with reasoning about a finite set of samples, this formulation improves the accuracy and efficiency of our model when a large number of samples would otherwise be needed. In order to accomplish this, we propose a novel variation on EquiFormerV2 that leverages a UNet-style encoder-decoder architecture to enlarge the number of points the model can handle. Our resulting method, which we name $\textit{OrbitGrasp}$, significantly outperforms baselines in both simulation and physical experiments., Comment: Conference on Robot Learning 2024

Recent work has shown diffusion models are an effective approach to learning the multimodal distributions arising from demonstration data in behavior cloning. However, a drawback of this approach is the need to learn a denoising function, which is significantly more complex than learning an explicit policy. In this work, we propose Equivariant Diffusion Policy, a novel diffusion policy learning method that leverages domain symmetries to obtain better sample efficiency and generalization in the denoising function. We theoretically analyze the $\mathrm{SO}(2)$ symmetry of full 6-DoF control and characterize when a diffusion model is $\mathrm{SO}(2)$-equivariant. We furthermore evaluate the method empirically on a set of 12 simulation tasks in MimicGen, and show that it obtains a success rate that is, on average, 21.9% higher than the baseline Diffusion Policy. We also evaluate the method on a real-world system to show that effective policies can be learned with relatively few training samples, whereas the baseline Diffusion Policy cannot., Comment: Conference on Robot Learning 2024, Oral Presentation

Controlling robots through natural language instructions in open-vocabulary scenarios is pivotal for enhancing human-robot collaboration and complex robot behavior synthesis. However, achieving this capability poses significant challenges due to the need for a system that can generalize from limited data to a wide range of tasks and environments. Existing methods rely on large, costly datasets and struggle with generalization. This paper introduces Grounded Equivariant Manipulation (GEM), a novel approach that leverages the generative capabilities of pre-trained vision-language models and geometric symmetries to facilitate few-shot and zero-shot learning for open-vocabulary robot manipulation tasks. Our experiments demonstrate GEM's high sample efficiency and superior generalization across diverse pick-and-place tasks in both simulation and real-world experiments, showcasing its ability to adapt to novel instructions and unseen objects with minimal data requirements. GEM advances a significant step forward in the domain of language-conditioned robot control, bridging the gap between semantic understanding and action generation in robotic systems.

Humans can imagine goal states during planning and perform actions to match those goals. In this work, we propose Imagination Policy, a novel multi-task key-frame policy network for solving high-precision pick and place tasks. Instead of learning actions directly, Imagination Policy generates point clouds to imagine desired states which are then translated to actions using rigid action estimation. This transforms action inference into a local generative task. We leverage pick and place symmetries underlying the tasks in the generation process and achieve extremely high sample efficiency and generalizability to unseen configurations. Finally, we demonstrate state-of-the-art performance across various tasks on the RLbench benchmark compared with several strong baselines.

A set $X$ is called Euclidean Ramsey if, for any $k$ and sufficiently large $n$, every $k$-colouring of $\mathbb{R}^n$ contains a monochromatic congruent copy of $X$. This notion was introduced by Erd\H{o}s, Graham, Montgomery, Rothschild, Spencer and Straus. They asked if a set is Ramsey if and only if it is spherical, meaning that it lies on the surface of a sphere. It is not too difficult to show that if a set is not spherical then it is not Euclidean Ramsey either, but the converse is very much open despite extensive research over the years. On the other hand, the block sets conjecture is a purely combinatorial, Hales-Jewett type of statement, concerning `blocks in large products', introduced by Leader, Russell and Walters. If true, the block sets conjecture would imply that every transitive set (a set whose symmetry group acts transitively) is Euclidean Ramsey. As for the question above, the block sets conjecture remains very elusive, being known only in a few cases. In this paper we show that the sizes of the blocks in the block sets conjecture cannot be bounded, even for templates over the alphabet of size $3$. We also show that for the first non-trivial template, namely $123$, the blocks may be taken to be of size $2$ (for any number of colours). This is best possible; all previous bounds were `tower-type' large., Comment: 10 pages

Many algorithms and observed phenomena in deep learning appear to be affected by parameter symmetries -- transformations of neural network parameters that do not change the underlying neural network function. These include linear mode connectivity, model merging, Bayesian neural network inference, metanetworks, and several other characteristics of optimization or loss-landscapes. However, theoretical analysis of the relationship between parameter space symmetries and these phenomena is difficult. In this work, we empirically investigate the impact of neural parameter symmetries by introducing new neural network architectures that have reduced parameter space symmetries. We develop two methods, with some provable guarantees, of modifying standard neural networks to reduce parameter space symmetries. With these new methods, we conduct a comprehensive experimental study consisting of multiple tasks aimed at assessing the effect of removing parameter symmetries. Our experiments reveal several interesting observations on the empirical impact of parameter symmetries; for instance, we observe linear mode connectivity between our networks without alignment of weight spaces, and we find that our networks allow for faster and more effective Bayesian neural network training. Our code is available at https://github.com/cptq/asymmetric-networks, Comment: NeurIPS 2024. v2: added / updated some citations. v3 added link to code, and some additional ablations

Completions play an important r\^ole for studying structure by supplying elements that in some sense ``ought to be." Among these, the Dedekind-MacNeille completion is of particular importance. In 1968 Janowitz provided necessary and sufficient conditions for it to be subfit or Boolean. Another natural separation axiom situated between the two is regularity. We explore similar characterizations of when closely related completions are subfit, regular, or Boolean. We are mainly interested in the Bruns-Lakser, ideal, and canonical completions, which are useful in pointfree topology since (unlike the Dedekind-MacNeille completion) they satisfy stronger forms of distributivity., Comment: 28 pages, 4 figures, 4 tables

Despite the advancements in learning governing differential equations from observations of dynamical systems, data-driven methods are often unaware of fundamental physical laws, such as frame invariance. As a result, these algorithms may search an unnecessarily large space and discover less accurate or overly complex equations. In this paper, we propose to leverage symmetry in automated equation discovery to compress the equation search space and improve the accuracy and simplicity of the learned equations. Specifically, we derive equivariance constraints from the time-independent symmetries of ODEs. Depending on the types of symmetries, we develop a pipeline for incorporating symmetry constraints into various equation discovery algorithms, including sparse regression and genetic programming. In experiments across diverse dynamical systems, our approach demonstrates better robustness against noise and recovers governing equations with significantly higher probability than baselines without symmetry. Our codebase is available at https://github.com/Rose-STL-Lab/symmetry-ode-discovery.

The recent advent of autonomous laboratories, coupled with algorithms for high-throughput screening and active learning, promises to accelerate materials discovery and innovation. As these autonomous systems grow in complexity, the demand for robust and efficient workflow management software becomes increasingly critical. In this paper, we introduce AlabOS, a general-purpose software framework for orchestrating experiments and managing resources, with an emphasis on automated laboratories for materials synthesis and characterization. AlabOS features a reconfigurable experiment workflow model and a resource reservation mechanism, enabling the simultaneous execution of varied workflows composed of modular tasks while eliminating conflicts between tasks. To showcase its capability, we demonstrate the implementation of AlabOS in a prototype autonomous materials laboratory, A-Lab, with around 3,500 samples synthesized over 1.5 years., Comment: 34 pages, 5 figures

The Simons Observatory (SO) is a cosmic microwave background (CMB) survey experiment that includes small-aperture telescopes (SATs) observing from an altitude of 5,200 m in the Atacama Desert in Chile. The SO SATs will cover six spectral bands between 27 and 280 GHz to search for primordial B-modes to a sensitivity of $\sigma(r)=0.002$, with quantified systematic errors well below this value. Each SAT is a self-contained cryogenic telescope with a 35$^\circ$ field of view, 42 cm diameter optical aperture, 40 K half-wave plate, 1 K refractive optics, and $<0.1$ K focal plane that holds $>12,000$ TES detectors. We describe the nominal design of the SATs and present details about the integration and testing for one operating at 93 and 145 GHz.

The intrinsic alignments (IA) of galaxies, regarded as a contaminant in weak lensing analyses, represents the correlation of galaxy shapes due to gravitational tidal interactions and galaxy formation processes. As such, understanding IA is paramount for accurate cosmological inferences from weak lensing surveys; however, one limitation to our understanding and mitigation of IA is expensive simulation-based modeling. In this work, we present a deep learning approach to emulate galaxy position-position ($\xi$), position-orientation ($\omega$), and orientation-orientation ($\eta$) correlation function measurements and uncertainties from halo occupation distribution-based mock galaxy catalogs. We find strong Pearson correlation values with the model across all three correlation functions and further predict aleatoric uncertainties through a mean-variance estimation training procedure. $\xi(r)$ predictions are generally accurate to $\leq10\%$. Our model also successfully captures the underlying signal of the noisier correlations $\omega(r)$ and $\eta(r)$, although with a lower average accuracy. We find that the model performance is inhibited by the stochasticity of the data, and will benefit from correlations averaged over multiple data realizations. Our code will be made open source upon journal publication., Comment: 15 pages, 6 figures, 1 table. Accepted at the Data-centric Machine Learning Research (DMLR) Workshop at ICLR 2024

We investigate whether the set of subfit elements of a distributive semilattice is an ideal. This question was raised by the second author at the BLAST conference in 2022. We show that in general it has a negative solution, however if the semilattice is a lattice, then the solution is positive. This is somewhat unexpected since, as we show, a semilattice is subfit if and only if so is its distributive lattice envelope., Comment: 14 pages, 1 figure

We describe the discrete Fourier transform (DFT) for a cyclic group when $p|N$ by factoring $x^N-1$ over finite fields and constructing the Fourier transform and its inverse using B\'{e}zout's identity for polynomials. For the symmetric group, in the modular case when $p|n!$ we construct the Peirce decomposition using central primitive orthogonal idempotents, yielding a change-of-basis matrix which generalizes the DFT. We compute the unitary DFT for the symmetric group over number fields containing sufficiently many square roots. For $n=3$, we compute the Galois group of the splitting field of the characteristic polynomial. All constructions are implemented in SageMath., Comment: 12 pages

Many physical and chemical processes in the condensed phase environment exhibit non-Markovian quantum dynamics. As such simulations are challenging on classical computers, we developed a variational quantum algorithm that is capable of simulating non-Markovian dynamics on NISQ devices. We used a quantum system linearly coupled to its harmonic bath as the model Hamiltonian. The non-Markovianity is captured by introducing auxiliary variables from the bath trajectories. With Monte Carlo sampling of the bath degrees of freedom, finite temperature dynamics is produced. We validated the algorithm on the simulator and demonstrated its performance on the IBM quantum device. The framework developed is naturally adapted to any anharmonic bath with non-linear coupling to the system, and is also well suited for simulating spin chain dynamics in a dissipative environment.