22 papers
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models
Samar Fares, Klea Ziu, Toluwani Aremu +5
Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To…
Information-Theoretic Upper Bounds for Deterministic Noise in Zeroth-Order Convex Optimization
Dmitry Pasechnyuk-Vilensky, Igor Pavlov, Martin TakÃ¡Ä +1
We study deterministic adversarial noise in zeroth-order convex optimization on Euclidean balls. The maximum admissible level of noise is the largest uniform error in function-valu…
Dual Advantage Fields
Alexey Zemtsov, Maxim Bobrin, Alexander Nikulin +5
Offline goal-conditioned reinforcement learning requires both long-horizon reachability estimates and local action comparisons. Dual goal representations provide value fields that…
Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods
Andrey Veprikov, Arman Bolatov, Aleksandr Bogdanov +4
Optimization lies at the core of modern deep learning, yet existing methods often face a fundamental trade-off between adapting to problem geometry and leveraging curvature utiliza…
Heterogeneous-Horizon Exact-Weight Local SGD
Dmitry Pasechnyuk-Vilensky, Martin TakáÄ
We study adaptive aggregation for heterogeneous local SGD in convex finite-sum optimization, allowing heterogeneous local horizons, minibatch sizes, gradient noise, and participati…
Cubic Regularized Newton Method with Variance Reduction for Finite-sum Non-convex Problems
Dmitry Pasechnyuk-Vilensky, Dmitry Kamzolov, Martin TakáÄ
We study finite-sum non-convex optimization and analyze a variance-reduced cubic Newton method based on EMA-smoo…