Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Garrigos, Guillaume"'
In this paper, we consider a deterministic online linear regression model where we allow the responses to be multivariate. To address this problem, we introduce MultiVAW, a method that extends the well-known Vovk-Azoury-Warmuth algorithm to the multi
Externí odkaz:
http://arxiv.org/abs/2402.14578
There are several applications of stochastic optimization where one can benefit from a robust estimate of the gradient. For example, domains such as distributed learning with corrupted nodes, the presence of large outliers in the training data, learn
Externí odkaz:
http://arxiv.org/abs/2402.12828
Here we develop variants of SGD (stochastic gradient descent) with an adaptive step size that make use of the sampled loss values. In particular, we focus on solving a finite sum-of-terms problem, also known as empirical risk minimization. We first d
Externí odkaz:
http://arxiv.org/abs/2307.14528
We study multi-product inventory control problems where a manager makes sequential replenishment decisions based on partial historical information in order to minimize its cumulative losses. Our motivation is to consider general demands, losses and d
Externí odkaz:
http://arxiv.org/abs/2307.06048
Black-box variational inference is widely used in situations where there is no proof that its stochastic optimization succeeds. We suggest this is due to a theoretical gap in existing stochastic optimization proofs: namely the challenge of gradient e
Externí odkaz:
http://arxiv.org/abs/2306.03638
Autor:
Garrigos, Guillaume, Gower, Robert M.
This is a handbook of simple proofs of the convergence of gradient and stochastic gradient descent type methods. We consider functions that are Lipschitz, smooth, convex, strongly convex, and/or Polyak-{\L}ojasiewicz functions. Our focus is on ``good
Externí odkaz:
http://arxiv.org/abs/2301.11235
Autor:
Garrigos, Guillaume
This short note gathers known results to state that the squared distance function to a (nonconvex) closed set of an Euclidean space is Polyak-{\L}ojasiewicz. As a fuzzy reciprocate, we also recall that every Polyak-{\L}ojasiewicz function can be boun
Externí odkaz:
http://arxiv.org/abs/2301.10332
Publikováno v:
Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:279-318, 2022
We present a principled approach for designing stochastic Newton methods for solving finite sum optimization problems. Our approach has two steps. First, we re-write the stationarity conditions as a system of nonlinear equations that associates each
Externí odkaz:
http://arxiv.org/abs/2106.10520
Publikováno v:
SIAM Journal on Optimization, 31(1), 754-784 (2021)
We propose and analyze an accelerated iterative dual diagonal descent algorithm for the solution of linear inverse problems with general regularization and data-fit functions. In particular, we develop an inertial approach of which we analyze both co
Externí odkaz:
http://arxiv.org/abs/1912.12153
Low-complexity non-smooth convex regularizers are routinely used to impose some structure (such as sparsity or low-rank) on the coefficients for linear predictors in supervised learning. Model consistency consists then in selecting the correct struct
Externí odkaz:
http://arxiv.org/abs/1803.08381