arXiv Machine Learning

Local Search with Correlated Randomness

arXiv AI
Sep 12

Probabilistic Focal Search: Accelerating Bounded-Suboptimal Search via Lower-Bound Advancement

Probabilistic Focal Search (PFS) augments traditional Focal Search by probabilistically choosing between the standard heuristic-guided expansion and expanding the minimum‑f node in OPEN. This strategy advances the lower bound, enlarges the FOCAL frontier, and can dramatically reduce node expansions—up to 90% in some benchmarks such as N‑Puzzle and TSP—especially when long f_min plateaus delay useful FOCAL admissions. An anytime variant, APFS, outperforms other tested anytime algorithms on the Generalized Covering TSP, and the same probabilistic scheduler transfers to Dynamic Potential Search as Probabilistic Dynamic Potential Search (PDPS), though its effectiveness varies by domain and bound.

By Minh Vu Duc, Trung Le Huu, H\`a Minh Ho\`ang, Trung Thanh Nguyen, Phuong Khanh Nguyen, Huynh Thi Thanh Binh
arXiv Machine Learning
Oct 22

A Sharp Dynamic Haussler Lemma

arXiv:2610. 29898v1 Announce Type: new Abstract: Haussler's covering lemma (JCTA 1995) gives the sharp $(C/\delta)^d$ metric-entropy bound for binary VC classes under normalized $\ell_1$ distance.

By Shihao Shao, Dacheng Tao
arXiv AI
3d ago

Introducing Feedback Delays to Non-Delayed Adversarial MDPs: Optimal $\sqrt S$ and $\sqrt K$ Dependencies in Tabular and Linear AMDPs

The paper introduces a technique called introduced feedback delays to improve regret bounds in episodic adversarial Markov Decision Processes (AMDPs). By estimating the Q‑function using future episodes while still updating the policy, the authors achieve µO(poly(H)√{SAK}) regret for tabular AMDPs and µO(poly(d,H)√{K}) regret for linear AMDPs, resolving long‑standing gaps. The method also extends to settings with actual feedback delays, providing optimal bounds in both state and delay dimensions.

By Aarush Kulkarni, Khang Nguyen, William Chang, Yan Dai
arXiv Machine Learning
6d ago

Learning from First Discrepancies with Joint Reset and Pilot Guarantees

The paper studies learning from runs that stop at their first incorrect decision, revealing only the queries and correct labels up to that point. It analyzes how many such runs are required to learn a hypothesis from a fixed binary class of VC dimension at most $d$, providing bounds on the number of runs and distinct pilots needed to achieve a risk estimate within ε of the optimal risk. The results include upper bounds on sample complexity, treatment of unknown cost ceilings, and matching lower bounds for finite classes.

By Michal \v{C}ert\'ik