Reward Biasing in RL: Tempered Optimism for Exploration Improves Performance (abstract)

A Piecewise Lyapunov Analysis of Sub-quadratic SGD: Applications to Robust and Quantile Regression (abstract)

Global Minimizers of Sigmoid Contrastive Loss (abstract)

Diffusion bridges and adversarial examples (abstract)

Reinforcement Learning from Human Feedback with an Unknown Link Function (abstract)

FedCostAware: Enabling Cost-Aware Federated Learning on the Cloud (abstract)

A Modular Federated Suite for Low-Rank, Expressive, and Efficient LLM Fine-Tuning (abstract)

Sketching for Distributed Deep Learning (abstract)

The Role of Private Synthetic Data in Collaborative Learning (abstract)

A time-reversal methodology for steering the state of control-affine stochastic systems (abstract)

An Operator Theoretic Viewpoint of Reinforcement Learning and a class of PPO Algorithms (abstract)

Path-Generalized I-MMSE: Bridging Diffusion and Autoregressive Generation (abstract)

A Stochastic-Control Lense unifying Transformers, Diffusions & Reinforcement Learning (abstract)

Probabilistic DiffusionNet: A geometry informed probabilistic neural operator (abstract)

Maximal Achievable Service Rates of Codes and Connections to Combinatorial Designs (abstract)

Communication Systems with Mismatched Encoder and Decoders (abstract)

An Upper Bound for Interactive ECCs with Separate Budgets (abstract)

Side Channel Communications With Ghost Modulation Over the Asymmetric Binary Crossover Erasure Channel (abstract)

Z-Channel Modeling of Hardware Trojans (abstract)

Allocating Shared Resources via Dynamic Max-Min Fairness (abstract)

Scalable and Convergent Algorithms for Strategically Risk-Averse Agents in Markov Games (abstract)

Principled Learning-to-Communicate with Quasi-Classical Information Structures (abstract)

Linear-Quadratic Stackelberg Differential Games for Jump-Diffusion Systems with Complete and Partial Information (abstract)

Differential Game Based Guidance with Delayed Engagement Decision (abstract)

The H-property for Asymmetric Graphons: The zero-one law (abstract)

A Reinforcement Learning View on the Sample Complexity of Linear Quadratic Regulator (abstract)

Measure Transport of Control Systems using Flow Matching (abstract)

When do practical Koopman embeddings exist? (abstract)

On the role of time scale in reservoir computing (abstract)

Unit Commitment without Commitment: The Network Setting (abstract)

Optimal Mechanisms for Demand Response: An Indifference Set Approach (abstract)

Battery Operations in Electricity Markets: Strategic Behavior and Distortions (abstract)

Optimal Battery Placement in Power Grid (abstract)

Risk Sharing Among Microgrids: Connectivity Requirements and Optimal Control (abstract)

Private Counterfactual Retrieval (abstract)

Rate-Distortion-Perception Trade-off in Summarization (abstract)

Towards a Unification of Logic and Information Theory (abstract)

Zero Perception Error Rate-Distortion for Semantic Communication (abstract)

Pessimism for Zero-Shot Transfer in RL (abstract)

A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch (abstract)

Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach (abstract)

A Malliavin Calculus based Weak-Derivative Approach for Training Neural Stochastic Differential Equations (abstract)

Robust Conditional Value-at-Risk Based Risk-Sensitive Reinforcement Learning (abstract)

Reliable and Adaptive Stochastic Optimization in the Face of Messy Data (abstract)

Learning with Episodic Hypothesis Testing in General Games (abstract)

On Speeding Up Language Model Evaluation (abstract)

HardNet: Hard-Constrained Neural Networks (abstract)

Pricing in Discrete Markets Using Copositive Duality (abstract)

System Opacity Formulations and Applications to Privacy Preservation in Smart Grids (abstract)

Inexactness of Second-order Cone Relaxations for Calculating Operating Envelopes (abstract)

Watts and Drops: Co-Scheduling Power and Water in Desalination Plants (abstract)

Model Expansion to Realize Preferred Topologies (abstract)

Optimal Setpoints of Current Constrained Converters-Based Resources (abstract)

Learning Without Forgetting (abstract)

Tensor Product Attention Is All You Need (abstract)

Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure (abstract)

Asymptotic convexity of wide and shallow neural networks (abstract)

Editing and inversion of images with flow models (abstract)

FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation (abstract)

Provable Posterior Sampling with Score-Based Diffusion via Tilted Transport (abstract)

DarkDiff: Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISP (abstract)

Distillation learns clean generative models from corrupted data (abstract)

Group Formation through Game Theory and Agent-Based Modeling: Spatial Cohesion, Heterogeneity, and Resource Pooling (abstract)

Coordination Games on Multiplex Networks: Consensus and Convergence of Opinion Dynamics (abstract)

On Myopia in Rationally Inattentive Dynamic Information Acquisition (abstract)

A Noncooperative Solution for Coalition Formation and Payoff Negotiation (abstract)

Compression for Incentivization (abstract)

Learning Neural Control Barrier Functions from Demonstrations (abstract)

Conservative Perception Models for Probabilistic Model Checking (abstract)

Co-Optimization of Perception and Control for Autonomous Systems (abstract)

Failure Prediction from Limited Hardware Demonstrations (abstract)

Abstractions for Scalable Analysis of AI-enabled Cyber-Physical Systems (CPS) (abstract)

Compositional Verification of Autonomous Systems (abstract)

Monotone dynamics in network control (abstract)

Join-the-Shortest-Queue with Markov-Modulated Parameters: Poisson Equation and Transform Techniques (abstract)

Sequential policies and the distribution of their total rewards in dynamic and stochastic knapsack problems (abstract)

Target-Following Online Resource Allocation Using Proxy Assignments (abstract)

Mixing Times for Reversible Countable State Markov Chains: A case study of the Erlang-C queue (abstract)

Dual-Sensor Quickest Change Detection with Sampling Control (abstract)

Bandit-Based Sequential Client Scheduling in Federated Learning (abstract)

Sequential Change Point Detection via Denoising Score Matching (abstract)

Cluster-Aware Causal Mixer for Sequential Change Detection in Multivariate Time Series (abstract)

Optimal Bounded-Influence Procedure for Robust Sequential Change-Point Detection (abstract)

Towards a Nudge-Theoretic Cyber Deception Framework (abstract)

On Subset Retrieval and Group Testing Problems with Differential Privacy Constraints (abstract)

Approximately Optimal Toll Design for Efficiency and Equity in Arc-Based Traffic Assignment Models (abstract)

Efficient and Privacy-Preserving Binary Dot Product via Multi-Party Computation (abstract)

If the Virus Respected Queues (abstract)

A theoretical basis for model collapse in recursive training (abstract)

Soft Training: Method for Neural Network Learning (abstract)

New Convergence Rates for Function Approximation Using Kernel Methods (abstract)

Joint Problems in Learning Multiple Dynamical Systems (abstract)

Artificial Parameter Based Approximate Solutions of Non-Symmetric Matrix Riccati Differential Equation (abstract)

LLM-Stackelberg Games: Conjectural Reasoning Equilibria, Meta-Cognition, and Applications to Spearphishing (abstract)

Deception against Game-Theoretic Learning in Complex Adaptive Systems (abstract)

Experimentation in the Presence of Strategic Buyers: Unbiased Estimation Under Intertemporal Substitution (abstract)

Persuasion under Dynamic Trust: Parametric Sender Behavior (abstract)

From signaling to interviews in random matching markets (abstract)

Stochastic model and decomposition schemes for relaxation oscillator based SAT solver (abstract)

Scheduling with Uncertain Holding Costs and its Application to Content Moderation (abstract)

Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs (abstract)

Dynamic Matching with Post-allocation Service and its Application to Refugee Resettlement (abstract)

Learning and predicting uncertain dynamical systems from data (abstract)

Hierarchical Implicit Neural Operators (abstract)

Confronting Uncertainty in AI for Science (abstract)

Foundation Models for Spatio-temporal Physics (abstract)

Automation and generative AI accelerated design of bio-therapeutics (abstract)

Exact Channel Simulation under Exponential Cost (abstract)

An Achievable Rate Region for Hypothesis Testing and User Identification with Multiple Sources (abstract)

Distributed Hypothesis Testing and the Output Statistics of Random Binning (abstract)

Source-Channel Coding in Multiple-Access Channels with Correlated Sources (abstract)

On Explicit Families of Outer Bounds for Broadcast Networks (abstract)

Reduced Complexity Encoding of Non-binary Quasi Cyclic Low-Density Parity-Check Codes (abstract)

Relaying Quantum Information (abstract)

A Cutting-plane Method for Semidefinite Programming with Potential Applications on Noisy Quantum Devices (abstract)

Winning Rates of (n, k) Quantum Coset Monogamy Games (abstract)

The Sum of Leaf Weights in the Minimum Spanning Tree of the Complete Graph (abstract)

Towards an optimal solution to NMF (abstract)

A Proof of The Changepoint Detection Threshold Conjecture in Preferential Attachment Models (abstract)

Active Generative Models for Inference and Learning in Complex Physical World (abstract)

Reliable Inference at Scale Using Graph Structure (abstract)

Optimal Change Detection in Multi-Armed Bandit (abstract)

Truncated LinUCB for Stochastic Linear Bandits (abstract)

Online Kernel CUSUM for Change-Point Detection (abstract)

On Prophet Inequalities for Markov Rewards (abstract)

Sequential Procedures for Early Detection of Machine Faults (abstract)

Quickest Quantum Change Point Detection (abstract)

Near-Field Quiet Zone Using Passive XL-RIS for 6G-IoT Coexistence in the Upper Mid-Band (abstract)

On Secrecy Capacity of Binary Beampointing Channels with Block Memory and Feedback (abstract)

The Pulse-Shaping Trojan: Refinements and New Results (abstract)

Optimizing Age of Information without Knowing the Age of Information (abstract)

On Estimation of Angles of Arrival in Monostatic ISAC Without Instantaneous Transmit CSI at the Transmiter (abstract)

Interpreting learned error-correcting codes (abstract)

Joint Constellation and Labeling Design for Gaussian Interference Channels via Autoencoders (abstract)

Regionally Robust Autoencoder-Based Channel Codes (abstract)

DPIR: Deep Predictive Interference-Aware Routing for Wireless Networks (abstract)

Single-Server SPIR over Binary Erasure Channels: Benefits of Noisy Side Information (abstract)

Leaky Multi-Message Private Information Retrieval with Differential Privacy Guarantees (abstract)

Improved Achievable Rate for Single Server SPIR over BEC (abstract)

Is Neural Network Verification Useful and What Is Next? (abstract)

Generating and Checking DNN Verification Proofs (abstract)

StarV: A Qualitative and Quantitative Verification Framework for Learning-enabled Autonomy (abstract)

Reachable and Invariant Sets of Neural Controlled Systems via a Monotone Embedding (abstract)

Analytical Lyapunov Function Discovery: An RL-based Generative Approach (abstract)

Bridging Learning and Reasoning: From Solvers to LLMs (abstract)

A Precise Performance Analysis of the Randomized Singular Value Decomposition (abstract)

Estimating Error in Natural Distribution Estimation (abstract)

Linking Diffusion Models & I-MMSE (abstract)

Bounds on the Privacy Amplification of Arbitrary Channels via the Contraction of $f_\alpha$-Divergence (abstract)

Information-Theoretic Outer-bounds from Sphere-Packing, Compactness, and Zero-One Laws (abstract)

Transformers Provably Learn Symbolic Multi-step Reasoning via Chain of Thought (abstract)

Reinforcement Learning Design for Quickest Change Detection - Extended Abstract (abstract)

Challenges of Reliable Training and Evaluation of Large Language Models (abstract)

Follow-the-Perturbed-Leader with Between-Action Dependence (abstract)

Toward a Theory of Data Ecology: Understanding and Steering Data Ecosystems (abstract)

Online Bipartite Matching with Advice (abstract)

Online Fair Allocation of Perishable Resources (abstract)

The Tarski Search Problem: Algorithms, Complexity, and Open Questions (abstract)

Optimal Data Acquisition with Privacy-Aware Agents (abstract)

Learning and inference from temporally dependent data (abstract)

Ordinal-Poisson Causal Discovery (abstract)

Focal Loss: Statistical and Information-Theoretic Perspectives (abstract)

Synchronizing Probabilities in Model-Driven Compression (abstract)

A FREQUENTIST THEORY FOR M-POSTERIORS: ASYMPTOTIC AND ROBUSTNESS PROPERTIES (abstract)

Optimal Sampling and Scheduling for Remote Fusion Estimation of Correlated Wiener Processes (abstract)

Optimizing Preventive and Reactive Defense Resource Allocation with Uncertain Sensor Signals (abstract)

Error-Sensitive Dynamic Calibration for Online Optimization with Switching Costs (abstract)

Control of Dynamical Systems with Multiplicative Observation Noise with Unknown Distribution Parameters (abstract)

Problem-dependent convergence bounds for randomized linear gradient compression (abstract)

BayesFlow++: A Unified Framework for Amortized Bayesian Inference in Complex Systems (abstract)

On the Sign Structure of the Ridge Estimator for Nonnegative Linear Mappings (abstract)

Hybrid Atomic Norm Sparse/Diffuse Channel Estimation (abstract)

Scaling Wideband Massive MIMO Radar via Beamspace Dimension Reduction (abstract)

Multi-Cell MMSE Processing and Pilot Assignment in Massive MIMO under Correlated Fading (abstract)

Optimal Service Mode Assignment in a Simple Computation Offloading System (abstract)

Distributed Caching of Transient Contents in a Tandem of Caches (abstract)

Variable Min-Cut Max-Flow Bounds and Algorithms in Finite Regime (abstract)

Version Age of Information with Contact Mobility in Gossip Networks (abstract)

Minimum-Latency Reliable Routing in Interference-Powered Networks (abstract)