Search

We conducted a theoretical study on the process $\Sigma^{+} p \to\Lambda a_0^{+} p$ based on an effective Lagrangian approach. This model encompasses the excitation of intermediate states leading to the production of $\Delta(1920)$ through $\pi^{+}$ and $K^{+}$ meson exchanges between the initial $\Sigma^{+}$ baryon and the initial proton $p$, as well as the generation of $\Delta(1940)$ via $\pi^{+}$ and $\rho^{+}$ meson exchanges. We provide predictions for the total and differential cross sections and discuss the potential impacts of cutoff parameters, off-shell effects, and branching ratios on the $\Delta^{\ast} \to a_0 p$ decay. Given the dominance of $\Delta(1940)$ in the region close to the reaction threshold, this reaction is considered an ideal platform for deeply exploring the unique properties of the $\Delta(1940)$ resonance. Through this approach, we can gain a more precise understanding of the intrinsic characteristics of this particle., Comment: 13 pages,10 figures

Quantum phase transitions (QPTs) between uniaxial or biaxial spin nematic (SN) phases are investigated in biquadratic spin-1 and spin-2 XY infinite chains with the rhombic- and uniaxial-type single-ion anisotropies. Systematic discussions of distinctive singular behaviors are made to classify various types of QPT from one SN state to the other SN state in using the Wigner-Yanase skew information (WYSI), the bipartite entanglement entropy (BEE), and the quadrupole moments (QMs). For the spin-1 system with the three uniaxial SN phases, we find that a discontinuous QPT, signaled by discontinuous behaviors of all the considered WYSI, BEE, and QMs, occurs from the z-ferroquadrupole phase (FQP) to the x- or y-FQPs, while a continuous QPT occurs between the x- and y-FQPs. The central charge in the continuous QPT line is estimated as $c \simeq 1$ from the BEE. Compared to the spin-1 system, depending on a given strength of the uniaxial-type single-ion anisotropy, the spin-2 system undergoes four different types of QPTs between the two biaxial SN phases as the rhombic-type anisotropy varies: the quantum crossovers, connecting the two orthogonal biaxial SN states adiabatically without an explicit phase transition, the continuous and the discontinuous QPTs, and the SN to magnetic transitions via the antiferromagnetic phase (AFP). In a sharp contrast to the spin-1 system, for the transitions between the two biaxial SN phases, the discontinuous transition line is classified as a topological phase characterized by a doubly degenerate entanglement spectrum and a string order parameter defined by the Cartan generator of the $\mathrm{SO}(5)$ symmetry group in spin-2 systems, while the continuous QPT is advocated by the central charge $c \simeq 1$. Whereas the QPT lines with $c \simeq 1/2$ indicate that the transition between the biaxial SN phase and the AFP belongs to the Ising universality class., Comment: 23 pages, 26 figures

In this paper, we present a novel algorithm, uniINF, for the Heavy-Tailed Multi-Armed Bandits (HTMAB) problem, demonstrating robustness and adaptability in both stochastic and adversarial environments. Unlike the stochastic MAB setting where loss distributions are stationary with time, our study extends to the adversarial setup, where losses are generated from heavy-tailed distributions that depend on both arms and time. Our novel algorithm `uniINF` enjoys the so-called Best-of-Both-Worlds (BoBW) property, performing optimally in both stochastic and adversarial environments without knowing the exact environment type. Moreover, our algorithm also possesses a Parameter-Free feature, i.e., it operates without the need of knowing the heavy-tail parameters $(\sigma, \alpha)$ a-priori. To be precise, uniINF ensures nearly-optimal regret in both stochastic and adversarial environments, matching the corresponding lower bounds when $(\sigma, \alpha)$ is known (up to logarithmic factors). To our knowledge, uniINF is the first parameter-free algorithm to achieve the BoBW property for the heavy-tailed MAB problem. Technically, we develop innovative techniques to achieve BoBW guarantees for Parameter-Free HTMABs, including a refined analysis for the dynamics of log-barrier, an auto-balancing learning rate scheduling scheme, an adaptive skipping-clipping loss tuning technique, and a stopping-time analysis for logarithmic regret.

Stochastic Network Optimization (SNO) concerns scheduling in stochastic queueing systems. It has been widely studied in network theory. Classical SNO algorithms require network conditions to be stationary with time, which fails to capture the non-stationary components in many real-world scenarios. Many existing algorithms also assume knowledge of network conditions before decision, which rules out applications where unpredictability presents. Motivated by these issues, we consider Adversarial Network Optimization (ANO) under bandit feedback. Specifically, we consider the task of *i)* maximizing some unknown and time-varying utility function associated to scheduler's actions, where *ii)* the underlying network is a non-stationary multi-hop one whose conditions change arbitrarily with time, and *iii)* only bandit feedback (effect of actually deployed actions) is revealed after decisions. Our proposed `UMO2` algorithm ensures network stability and also matches the utility maximization performance of any "mildly varying" reference policy up to a polynomially decaying gap. To our knowledge, no previous ANO algorithm handled multi-hop networks or achieved utility guarantees under bandit feedback, whereas ours can do both. Technically, our method builds upon a novel integration of online learning into Lyapunov analyses: To handle complex inter-dependencies among queues in multi-hop networks, we propose meticulous techniques to balance online learning and Lyapunov arguments. To tackle the learning obstacles due to potentially unbounded queue sizes, we design a new online linear optimization algorithm that automatically adapts to loss magnitudes. To maximize utility, we propose a bandit convex optimization algorithm with novel queue-dependent learning rate scheduling that suites drastically varying queue lengths. Our new insights in online learning can be of independent interest.

This paper presents a topological analytics approach within the 5-level Cyber-Physical Systems (CPS) architecture for the Stream-of-Quality assessment in smart manufacturing. The proposed methodology not only enables real-time quality monitoring and predictive analytics but also discovers the hidden relationships between quality features and process parameters across different manufacturing processes. A case study in additive manufacturing was used to demonstrate the feasibility of the proposed methodology to maintain high product quality and adapt to product quality variations. This paper demonstrates how topological graph visualization can be effectively used for the real-time identification of new representative data through the Stream-of-Quality assessment., Comment: The paper has been submitted to Manufacturing Letters (Under Review)

Markov Games (MG) is an important model for Multi-Agent Reinforcement Learning (MARL). It was long believed that the "curse of multi-agents" (i.e., the algorithmic performance drops exponentially with the number of agents) is unavoidable until several recent works (Daskalakis et al., 2023; Cui et al., 2023; Wang et al., 2023). While these works resolved the curse of multi-agents, when the state spaces are prohibitively large and (linear) function approximations are deployed, they either had a slower convergence rate of $O(T^{-1/4})$ or brought a polynomial dependency on the number of actions $A_{\max}$ -- which is avoidable in single-agent cases even when the loss functions can arbitrarily vary with time. This paper first refines the AVLPR framework by Wang et al. (2023), with an insight of designing *data-dependent* (i.e., stochastic) pessimistic estimation of the sub-optimality gap, allowing a broader choice of plug-in algorithms. When specialized to MGs with independent linear function approximations, we propose novel *action-dependent bonuses* to cover occasionally extreme estimation errors. With the help of state-of-the-art techniques from the single-agent RL literature, we give the first algorithm that tackles the curse of multi-agents, attains the optimal $O(T^{-1/2})$ convergence rate, and avoids $\text{poly}(A_{\max})$ dependency simultaneously., Comment: Accepted for presentation at the Conference on Learning Theory (COLT) 2024

Despite the success of the Adam optimizer in practice, the theoretical understanding of its algorithmic components still remains limited. In particular, most existing analyses of Adam show the convergence rate that can be simply achieved by non-adative algorithms like SGD. In this work, we provide a different perspective based on online learning that underscores the importance of Adam's algorithmic components. Inspired by Cutkosky et al. (2023), we consider the framework called online learning of updates/increments, where we choose the updates/increments of an optimizer based on an online learner. With this framework, the design of a good optimizer is reduced to the design of a good online learner. Our main observation is that Adam corresponds to a principled online learning framework called Follow-the-Regularized-Leader (FTRL). Building on this observation, we study the benefits of its algorithmic components from the online learning perspective., Comment: Accepted at ICML 2024

The ground-state phase diagram is mapped out for an alternative anisotropic extension of quantum spin-1 ferromagnetic biquadratic model, which accommodates twelve distinct phases: three degenerate fractal phases, six Luttinger liquid phases and three symmetry-protected trivial phases. It is found that distinct types of quantum phase transitions are involved between them. In particular, one type arises from an instability of a Luttinger liquid towards a degenerate fractal phase, and the other type describes spontaneous symmetry breaking with type-B Goldstone modes from one degenerate fractal phase to another degenerate fractal phase, with the fractal dimension $d_f$ being identical to the number of the type-B Goldstone modes, both of which turn out to be one. In addition, quantum phase transitions from the Luttinger liquid phases to the symmetry-protected trivial phases are identified to be in the Kosterlitz-Thouless universality class, with central charge being one., Comment: 11 pages, 8 figures, 2 tables

An emergent gapless Goldstone mode originates from continuous spontaneous symmetry breaking, which has become a doctrine since the pioneering work by Goldstone [J. Goldstone, Nuovo Cimento \textbf{19}, 154 (1961)]. However, we argue that it is possible for a continuous symmetry group $\rm{U}(1)$ to make an exceptional case, simply due to the well-known mathematical result that a continuous symmetry group $\rm{U}(1)$ may be regarded as a limit of a discrete symmetry group $Z_q$ when $q$ tends to infinity. As a consequence, spontaneous symmetry breaking for such a continuous symmetry group $\rm{U}(1)$ does not necessarily lead to any gapless Goldstone mode. This is explicitly explained for an anisotropic extension of the ferromagnetic spin-1 biquadratic model. In a sense, this model provides an illustrative example regarding the dichotomy between continuity and discreteness., Comment: 13 pages, 9 figures, 9 tables

A generic scheme is proposed to perform a finite-entanglement scaling analysis for scale-invariant states, which appear to be highly degenerate ground states arising from spontaneous symmetry breaking with type-B Goldstone modes. This allows us to extract the number of type-B Goldstone modes and the dynamical critical exponent, in combination with a finite block-size scaling analysis, from numerical simulations of quantum many-body systems in the context of tensor network representations. The number of type-B Goldstone modes is identical to the fractal dimension, thus reflecting an abstract fractal underlying the ground state subspace. As illustrative examples, we investigate the spin-$s$ Heisenberg ferromagnetic model, the $\rm{SU}(3)$ ferromagnetic model and the $\rm{SO}(4)$ spin-orbital model., Comment: 14 pages, 24 figures, 11 tables

Sharpness-Aware Minimization (SAM) is a recently proposed gradient-based optimizer (Foret et al., ICLR 2021) that greatly improves the prediction performance of deep neural networks. Consequently, there has been a surge of interest in explaining its empirical success. We focus, in particular, on understanding the role played by normalization, a key component of the SAM updates. We theoretically and empirically study the effect of normalization in SAM for both convex and non-convex functions, revealing two key roles played by normalization: i) it helps in stabilizing the algorithm; and ii) it enables the algorithm to drift along a continuum (manifold) of minima -- a property identified by recent theoretical works that is the key to better performance. We further argue that these two properties of normalization make SAM robust against the choice of hyper-parameters, supporting the practicality of SAM. Our conclusions are backed by various experiments., Comment: 30 pages, Published in 37th Neural Information Processing Systems (NeurIPS 2023)

We consider learning in an adversarial Markov Decision Process (MDP) where the loss functions can change arbitrarily over $K$ episodes and the state space can be arbitrarily large. We assume that the Q-function of any policy is linear in some known features, that is, a linear function approximation exists. The best existing regret upper bound for this setting (Luo et al., 2021) is of order $\tilde{\mathcal O}(K^{2/3})$ (omitting all other dependencies), given access to a simulator. This paper provides two algorithms that improve the regret to $\tilde{\mathcal O}(\sqrt K)$ in the same setting. Our first algorithm makes use of a refined analysis of the Follow-the-Regularized-Leader (FTRL) algorithm with the log-barrier regularizer. This analysis allows the loss estimators to be arbitrarily negative and might be of independent interest. Our second algorithm develops a magnitude-reduced loss estimator, further removing the polynomial dependency on the number of actions in the first algorithm and leading to the optimal regret bound (up to logarithmic terms and dependency on the horizon). Moreover, we also extend the first algorithm to simulator-free linear MDPs, which achieves $\tilde{\mathcal O}(K^{8/9})$ regret and greatly improves over the best existing bound $\tilde{\mathcal O}(K^{14/15})$. This algorithm relies on a better alternative to the Matrix Geometric Resampling procedure by Neu & Olkhovskaya (2020), which could again be of independent interest., Comment: Accepted to ICML 2023

We propose Banker Online Mirror Descent (Banker-OMD), a novel framework generalizing the classical Online Mirror Descent (OMD) technique in the online learning literature. The Banker-OMD framework almost completely decouples feedback delay handling and the task-specific OMD algorithm design, thus facilitating the design of new algorithms capable of efficiently and robustly handling feedback delays. Specifically, it offers a general methodology for achieving $\widetilde{\mathcal O}(\sqrt{T} + \sqrt{D})$-style regret bounds in online bandit learning tasks with delayed feedback, where $T$ is the number of rounds and $D$ is the total feedback delay. We demonstrate the power of \texttt{Banker-OMD} by applications to two important bandit learning scenarios with delayed feedback, including delayed scale-free adversarial Multi-Armed Bandits (MAB) and delayed adversarial linear bandits. \texttt{Banker-OMD} leads to the first delayed scale-free adversarial MAB algorithm achieving $\widetilde{\mathcal O}(\sqrt{K}L(\sqrt T+\sqrt D))$ regret and the first delayed adversarial linear bandit algorithm achieving $\widetilde{\mathcal O}(\text{poly}(n)(\sqrt{T} + \sqrt{D}))$ regret. As a corollary, the first application also implies $\widetilde{\mathcal O}(\sqrt{KT}L)$ regret for non-delayed scale-free adversarial MABs, which is the first to match the $\Omega(\sqrt{KT}L)$ lower bound up to logarithmic factors and can be of independent interest., Comment: Based on preliminary works arXiv:2106.08943 and arXiv:2110.13400; Accepted by ICML2023

Objectives: To develop a joint k-TE reconstruction algorithm to reconstruct the T2-weighted (T2W) images and T2 map simultaneously. Materials and Methods: The joint k-TE reconstruction model was formulated as an optimization problem subject to a self-consistency condition of the exponential decay relationship between the T2W images and T2 map. The objective function included a data fidelity term enforcing the agreement between the solution and the measured k-space data, together with a spatial regularization term on image properties of the T2W images. The optimization problem was solved using Alternating-Direction Method of Multipliers (ADMM). We tested the joint k-TE method in phantom data and healthy volunteer scans with fully-sampled and under-sampled k-space lines. Image quality of the reconstructed T2W images and T2 map, and the accuracy of T2 measurements derived by the joint k- TE and the conventional signal fitting method were compared. Results: The proposed method improved image quality with reduced noise and less artifacts on both T2W images and T2 map, and increased measurement consistency in T2 relaxation time measurements compared with the conventional method in all data sets. Conclusions: The proposed reconstruction method outperformed the conventional magnitude image-based signal fitting method in image quality and stability of quantitative T2 measurements, Comment: 25 pages, 4 figures, 2 tables

Skeleton-based action recognition aims to project skeleton sequences to action categories, where skeleton sequences are derived from multiple forms of pre-detected points. Compared with earlier methods that focus on exploring single-form skeletons via Graph Convolutional Networks (GCNs), existing methods tend to improve GCNs by leveraging multi-form skeletons due to their complementary cues. However, these methods (either adapting structure of GCNs or model ensemble) require the co-existence of all forms of skeletons during both training and inference stages, while a typical situation in real life is the existence of only partial forms for inference. To tackle this issue, we present Adaptive Cross-Form Learning (ACFL), which empowers well-designed GCNs to generate complementary representation from single-form skeletons without changing model capacity. Specifically, each GCN model in ACFL not only learns action representation from the single-form skeletons, but also adaptively mimics useful representations derived from other forms of skeletons. In this way, each GCN can learn how to strengthen what has been learned, thus exploiting model potential and facilitating action recognition as well. Extensive experiments conducted on three challenging benchmarks, i.e., NTU-RGB+D 120, NTU-RGB+D 60 and UAV-Human, demonstrate the effectiveness and generalizability of the proposed method. Specifically, the ACFL significantly improves various GCN models (i.e., CTR-GCN, MS-G3D, and Shift-GCN), achieving a new record for skeleton-based action recognition.

We consider regret minimization for Adversarial Markov Decision Processes (AMDPs), where the loss functions are changing over time and adversarially chosen, and the learner only observes the losses for the visited state-action pairs (i.e., bandit feedback). While there has been a surge of studies on this problem using Online-Mirror-Descent (OMD) methods, very little is known about the Follow-the-Perturbed-Leader (FTPL) methods, which are usually computationally more efficient and also easier to implement since it only requires solving an offline planning problem. Motivated by this, we take a closer look at FTPL for learning AMDPs, starting from the standard episodic finite-horizon setting. We find some unique and intriguing difficulties in the analysis and propose a workaround to eventually show that FTPL is also able to achieve near-optimal regret bounds in this case. More importantly, we then find two significant applications: First, the analysis of FTPL turns out to be readily generalizable to delayed bandit feedback with order-optimal regret, while OMD methods exhibit extra difficulties (Jin et al., 2022). Second, using FTPL, we also develop the first no-regret algorithm for learning communicating AMDPs in the infinite-horizon setting with bandit feedback and stochastic transitions. Our algorithm is efficient assuming access to an offline planning oracle, while even for the easier full-information setting, the only existing algorithm (Chandrasekaran and Tewari, 2021) is computationally inefficient., Comment: Accepted to NeurIPS 2022

It is well-known that for sparse linear bandits, when ignoring the dependency on sparsity which is much smaller than the ambient dimension, the worst-case minimax regret is $\widetilde{\Theta}\left(\sqrt{dT}\right)$ where $d$ is the ambient dimension and $T$ is the number of rounds. On the other hand, in the benign setting where there is no noise and the action set is the unit sphere, one can use divide-and-conquer to achieve $\widetilde{\mathcal O}(1)$ regret, which is (nearly) independent of $d$ and $T$. In this paper, we present the first variance-aware regret guarantee for sparse linear bandits: $\widetilde{\mathcal O}\left(\sqrt{d\sum_{t=1}^T \sigma_t^2} + 1\right)$, where $\sigma_t^2$ is the variance of the noise at the $t$-th round. This bound naturally interpolates the regret bounds for the worst-case constant-variance regime (i.e., $\sigma_t \equiv \Omega(1)$) and the benign deterministic regimes (i.e., $\sigma_t \equiv 0$). To achieve this variance-aware regret guarantee, we develop a general framework that converts any variance-aware linear bandit algorithm to a variance-aware algorithm for sparse linear bandits in a "black-box" manner. Specifically, we take two recent algorithms as black boxes to illustrate that the claimed bounds indeed hold, where the first algorithm can handle unknown-variance cases and the second one is more efficient., Comment: Accepted to ICLR 2023

An extensive investigation, both numerical and analytical, is performed for an anisotropic extension of the ferromagnetic spin-1 biquadratic model. The ground state phase diagram accommodates three symmetry-protected trivial phases, three coexisting fractal phases and six Luttinger liquid phases. A novel universality class arises from an instability of a Luttinger liquid towards an exotic quantum state of matter with infinitely degenerate ground states. The latter in turn is a scale-invariant quantum state of matter, which may be attributed to the coexistence of ${\rm SU}(2)$ spontaneous symmetry breaking with one type-B Goldstone mode on the characteristic line: $J_y=J_z$, and ${\rm U}(1)$ spontaneous symmetry breaking without any gapless Goldstone mode on the characteristic line $J_x/J_z=0$, together with their cyclic permutations with respect to $x$, $y$ and $z$., Comment: 11+ pages, 12 figures and 2 tables