Archives AI News

T-TAMER: Provably Taming Trade-offs in ML Serving

arXiv:2509.22992v1 Announce Type: new Abstract: As machine learning models continue to grow in size and complexity, efficient serving faces increasingly broad trade-offs spanning accuracy, latency, resource usage, and other objectives. Multi-model serving further complicates these trade-offs; for example, in cascaded…

Is Thompson Sampling Susceptible to Algorithmic Collusion?

arXiv:2405.17463v2 Announce Type: replace-cross Abstract: When two players are engaged in a repeated game with unknown payoff matrices, they may use single-agent multi-armed bandit algorithms to choose the actions independent of each other. We show that when the players use…

MDP modeling for multi-stage stochastic programs

arXiv:2509.22981v1 Announce Type: new Abstract: We study a class of multi-stage stochastic programs, which incorporate modeling features from Markov decision processes (MDPs). This class includes structured MDPs with continuous state and action spaces. We extend policy graphs to include decision-dependent…

Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search

arXiv:2509.15927v2 Announce Type: replace Abstract: Auto-bidding serves as a critical tool for advertisers to improve their advertising performance. Recent progress has demonstrated that AI-Generated Bidding (AIGB), which learns a conditional generative planner from offline data, achieves superior performance compared to…

OptiMind: Teaching LLMs to Think Like Optimization Experts

arXiv:2509.22979v1 Announce Type: new Abstract: Mathematical programming — the task of expressing operations and decision-making problems in precise mathematical language — is fundamental across domains, yet remains a skill-intensive process requiring operations research expertise. Recent advances in large language models…

Adaptive Sample Scheduling for Direct Preference Optimization

arXiv:2506.17252v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, its performance is highly dependent on the quality of the underlying human preference data. To…

Functional Critic Modeling for Provably Convergent Off-Policy Actor-Critic

arXiv:2509.22964v1 Announce Type: new Abstract: Off-policy reinforcement learning (RL) with function approximation offers an effective way to improve sample efficiency by reusing past experience. Within this setting, the actor-critic (AC) framework has achieved strong empirical success. However, both the critic…

Variational Deep Learning via Implicit Regularization

arXiv:2505.20235v2 Announce Type: replace Abstract: Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization imposed by the choice of architecture, hyperparameters and optimization procedure.…