Robuta

https://jmlr.org/papers/v27/25-0549.html Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection mirror descent max margin optimizing attention generalized https://jmlr.org/papers/v23/21-1027.html Online Mirror Descent and Dual Averaging: Keeping Pace in the Dynamic Case online mirror descent https://deepai.org/publication/adaptive-importance-sampling-meets-mirror-descent-a-bias-variance-tradeoff Adaptive Importance Sampling meets Mirror Descent: a Bias-variance tradeoff | DeepAI Oct 29, 2021 - 10/29/21 - Adaptive importance sampling is a widely spread Monte Carlo technique that uses a re-weighting strategy to iteratively estimate th... bias variance tradeoff importance sampling mirror descent adaptive meets https://openreview.net/forum?id=huT1G2dtSr Robust Imitation via Mirror Descent Inverse Reinforcement Learning | OpenReview we present a novel algorithm that provides rewards as iterative optimization targets for an imitation learning agent. mirror descent reinforcement learning robust imitation via https://openreview.net/forum?id=0SVOleKNRAU Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently | OpenReview Driven by the empirical success and wide use of deep neural networks, understanding the generalization performance of overparameterized models has become an... mirror descent generalized margin https://deepai.org/publication/stochastic-mirror-descent-convergence-analysis-and-adaptive-variants-via-the-mirror-stochastic-polyak-stepsize Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic... Oct 28, 2021 - 10/28/21 - We investigate the convergence of stochastic mirror descent (SMD) in relatively smooth and smooth convex optimization. In relative... mirror descent stochastic convergence analysis adaptive https://arxiv.org/abs/1202.3323 [1202.3323] Mirror Descent Meets Fixed Share (and feels no regret) Abstract page for arXiv paper 1202.3323: Mirror Descent Meets Fixed Share (and feels no regret) mirror descent 1202 3323 meets https://openreview.net/forum?id=Re6QSi8hXQ Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning | OpenReview The work uses mirror descent theory to accelerate model based RL for direct training on hardware. model predictive control mirror descent https://arxiv.org/abs/1210.4893 [1210.4893] Sparse Q-learning with Mirror Descent Abstract page for arXiv paper 1210.4893: Sparse Q-learning with Mirror Descent q learning 1210 4893 sparse mirror https://www.mit.edu/~gfarina/2025/67220s25_L14_mirror_descent/ Gabriele Farina - Projected gradient descent and mirror descent The projected gradient descent (PGD) algorithm; distance-generating functions and Bregman divergences; proximal steps and their properties; the mirror descent... projected gradient descent gabriele farina mirror https://deepai.org/publication/a-mirror-descent-approach-for-mean-field-control-applied-to-demande-side-management A mirror descent approach for Mean Field Control applied to Demande-Side management | DeepAI Feb 16, 2023 - 02/16/23 - We consider a finite-horizon Mean Field Control problem for Markovian models. The objective function is composed of a sum of conve... https://jmlr.org/papers/v27/24-0792.html A Symplectic Analysis of Alternating Mirror Descent symplectic analysis alternating mirror descent