Mathematical Foundations

arXiv:2408.14575v5 Announce Type: replace Abstract: EVINCE (Entropy and Variation IN Conditional Exchanges) is a novel framework for optimizing multi-LLM dialog

arXiv:2609.13703v1 Announce Type: cross Abstract: In the best-arm identification problem, we are given $n$ stochastic arms with unknown means and wish to identi

arXiv:2609.15838v1 Announce Type: cross Abstract: Per-matrix singular value decomposition (SVD) truncation is Eckart-Young optimal in the whitened Frobenius nor

arXiv:2609.06921v2 Announce Type: replace-cross Abstract: We study constrained online convex optimization with adversarial constraints and conditionally unbiase

arXiv:2609.12463v1 Announce Type: cross Abstract: We formulate and analyze the linear exponential quadratic Gaussian (LEQG) covariance steering problem in conti

arXiv:2608.28853v1 Announce Type: cross Abstract: Equivariant graph neural networks provide a principled way to model geometric systems, but efficient first-ord

arXiv:2608.29507v1 Announce Type: cross Abstract: Diffusion models are increasingly used not only for sampling from learned data distributions, but also for gen

arXiv:2505.22973v3 Announce Type: replace-cross Abstract: Diffusion models represent the state-of-the-art for solving inverse problems such as image restoration

arXiv:2608.27839v1 Announce Type: new Abstract: Fine-tuning-based knowledge editing is simple and architecture-agnostic, but standard cross-entropy increases th

arXiv:2608.27507v1 Announce Type: cross Abstract: Policy Gradient for Parallel State Entropy maximization (PGPSE) expands state-space coverage by training indep

arXiv:2608.26549v1 Announce Type: cross Abstract: While Physics-Informed Neural Networks (PINNs) have emerged as a transformative paradigm for solving complex d

arXiv:2608.24386v1 Announce Type: cross Abstract: Tensor-valued prediction is fundamental to geometric deep learning, yet uncertainty quantification (UQ) for su

arXiv:2608.24568v1 Announce Type: cross Abstract: Deep neural networks generalize well despite their highly nonconvex, overparameterized loss landscapes, a phen

arXiv:2608.22994v1 Announce Type: cross Abstract: Training large language models is costly. How low a loss the same compute can ultimately reach depends on how

framework that folds aggregate human movement into text-based place embeddings. Language models describe what a place is; they miss how it is used. ME-POIs enco

arXiv:2608.20802v1 Announce Type: new Abstract: Human motion forecasters are increasingly accurate and fast, but reliable deployment requires uncertainty estima

arXiv:2407.02765v4 Announce Type: replace-cross Abstract: We study the distributed optimization problem over a graphon with a continuum of nodes, which is regar

arXiv:2608.18147v1 Announce Type: cross Abstract: Adaptive stochastic quantization (ASQ) is a recently introduced quantization approach that optimizes the Mean

arXiv:2407.05788v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) is an efficient framework for optimization of black-box objectives when fun

arXiv:2608.17434v1 Announce Type: new Abstract: We study Gaussian regression over the explicit vector-valued Parhi--Nowak deep-RBV^2 architecture with depth L,

arXiv:2502.00213v5 Announce Type: replace-cross Abstract: Transformers are difficult to optimize with stochastic gradient descent (SGD) and largely rely on adap

arXiv:2507.15455v3 Announce Type: replace-cross Abstract: We propose a mesh-free policy iteration framework that combines classical dynamic programming with phy

arXiv:2608.14559v1 Announce Type: new Abstract: Effective communication in multi-agent reinforcement learning requires agents to decide not only \textit{what} t

arXiv:2608.16697v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) integrate visual perception, language instruction, and action generation in

arXiv:2608.14712v1 Announce Type: cross Abstract: Each row of a transformer's attention matrix is a probability distribution over tokens, and in trained models

arXiv:2608.13621v1 Announce Type: new Abstract: A hidden Markov model (HMM) combines three roles: inference of a hidden-state belief from observations, propagat

arXiv:2608.14126v1 Announce Type: cross Abstract: To mitigate attention dilution in high-entropy TLS 1.3 flows, we propose BGA, a noise-immune neural distillati

arXiv:2608.14264v1 Announce Type: cross Abstract: Model merging combines trained models directly in weight space, offering a compute-efficient alternative to ad

arXiv:2608.11749v1 Announce Type: cross Abstract: Multi-objective optimization (MOO) has demonstrated significant success in multi-task learning by mitigating t

arXiv:2608.12196v1 Announce Type: cross Abstract: Purpose: Deep learning-based medical image segmentation has achieved remarkable success, yet purely data-drive

arXiv:2608.09335v1 Announce Type: new Abstract: Multistage stochastic model predictive control (MPC) handles uncertainty by optimizing over a scenario tree, a f

arXiv:2608.09071v1 Announce Type: cross Abstract: Forward uncertainty propagation in complex physical systems can induce structured covariance across field-valu

arXiv:2307.10053v5 Announce Type: replace-cross Abstract: In this paper, we focus on providing convergence guarantees for stochastic subgradient methods in mini

arXiv:2607.05835v1 Announce Type: cross Abstract: For every loopless matroid $M$ and every Feichtner--Yuzvinsky building set $\mathcal{G}$ containing the top fl

Here’s a problem you probably didn’t solve in school: You’re an ambitious young plumber from Brooklyn in a world inhabited by violent human-size mushrooms calle

arXiv:2606.09926v1 Announce Type: cross Abstract: Sampling from the sequence-level power distribution $p^\alpha$ elicits RL-level reasoning from base language m

arXiv:2605.28078v1 Announce Type: cross Abstract: We design a class of additive noise mechanisms that satisfy \((\varepsilon, \delta)\)-differential privacy (DP

arXiv:2605.15407v1 Announce Type: cross Abstract: We consider amortized Bayesian inference for nonlinear inverse problems in settings where only samples from th

arXiv:2605.15417v1 Announce Type: cross Abstract: In GFlowNets and variational inference, it has been shown that the mean square error between target and model

arXiv:2605.15507v1 Announce Type: cross Abstract: For a Gaussian source under mean-squared error (MSE), classical transform coding is rate--distortion (RD) opti

arXiv:2605.14599v1 Announce Type: cross Abstract: We establish novel structural and statistical results for entropy-regularized min-max inverse reinforcement le

arXiv:2605.08794v1 Announce Type: cross Abstract: Modern generative models can be understood as probability transport from a simple base distribution to a targe

arXiv:2605.10402v1 Announce Type: cross Abstract: A finite presentation of a finite group is called `just finite' if removing any relation from R results in a p

arXiv:2604.23468v2 Announce Type: cross Abstract: In 2016, Viazovska famously solved the sphere packing problem in dimension $8$, using modular forms to constru

arXiv:2604.20882v1 Announce Type: cross Abstract: Quantum algorithms with a proven theoretical speedup over classical computation are rare. Among the most promi

arXiv:2604.14484v1 Announce Type: cross Abstract: Behavior cloning (BC) policies on position-controlled robots inherit the closed-loop response of the underlyin