arXiv Machine Learning August 10, 2026 By Ibne Farabi Shihab, Joyanta Jyoti Mondal

Sub-Quadratic Bisimulation Metrics via Approximate Nearest Neighbors: Coverage-Augmented Guarantees and Computable Two-Sided Certificates

Read the original on arXiv Machine Learning →

arXiv:2608. 06762v1 Announce Type: new Abstract: Bisimulation metrics quantify behavioral similarity in Markov decision processes, but their Wasserstein fixed-point operator updates every state pair and incurs quadratic pairwise work.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 16

Filtered ANN as a Phase Transition: When Selectivity-Estimation Error Causes Plan Regret

arXiv:2606. 16341v1 Announce Type: new Abstract: A filtered approximate-nearest-neighbor (ANN) query returns the k nearest vectors among those satisfying an attribute predicate P of selectivity s.

By Madhulatha Mandarapu, Sandeep Kunkunuru

arXiv Machine Learning

Jun 2

Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity

arXiv:2606. 00414v1 Announce Type: new Abstract: When many reinforcement-learning policies achieve near-optimal return, a post-hoc auditor may have to distinguish among many behaviorally distinct but return-equivalent policies.

By Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

reinforcement-learning benchmarks

arXiv Machine Learning

5d ago

Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation

arXiv:2606. 21253v2 Announce Type: replace Abstract: Continual learning that is gradient-free, local, online, and append-only is attractive for edge and streaming deployment, but its value is usually argued informally.

By Jianwei Lou (RailMind Systems, Neuss, Germany)

agents computer-vision

arXiv Machine Learning

Aug 11

The Cost of Adaptivity: Matching Lower Bounds Across Learning Problems

arXiv:2608. 08826v1 Announce Type: new Abstract: Adaptive procedures must work without nuisance information an oracle may use, such as a gradient scale or smoothness index, and robust procedures may have to answer queries whose coordinate and inspection time are chosen only after the data are seen.

By Ibne Farabi Shihab, Adria Binte Habib

benchmarks

arXiv AI

Jul 16

Price of Fairness in Bandits: A Tight Minimax Characterization

arXiv:2607. 13402v1 Announce Type: cross Abstract: In bandit problems, standard regret-minimizing algorithms treat exploration as an amortized cost, which can expose early participants to unfair ex-ante losses in settings such as clinical trials.

By Dhruv Sarkar, Soumyadeep Dutta, Sayak Ray Chowdhury

reinforcement-learning safety

arXiv AI

Jun 4

Exact Unlearning in Reinforcement Learning

arXiv:2606. 04182v1 Announce Type: cross Abstract: We formulate the problem of \emph{exact unlearning} in reinforcement learning, where the goal is to design an efficient framework that enables the removal of any user's data upon deletion request, i.

By Thanh Nguyen-Tang, Raman Arora

reinforcement-learning

Related stories

Filtered ANN as a Phase Transition: When Selectivity-Estimation Error Causes Plan Regret

Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity

Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation

The Cost of Adaptivity: Matching Lower Bounds Across Learning Problems

Price of Fairness in Bandits: A Tight Minimax Characterization

Exact Unlearning in Reinforcement Learning