Neural Information Processing Systems http://nips.cc/

This paper studies minimax optimization problemsminxmaxyf(x,y), where f(x,y) is mx-strongly convex with respect tox, my-strongly concave with respect to y and (Lx,Lxy,Ly)-smooth. Zhang et al. [42] provided the following lower bound of the gradient complexity for any first-order method: Ω q

We present a class of algorithms for state estimation in nonlinear, non-Gaussian state-space models. Our approach is based on a variational Lagrangian formulation that casts Bayesian inference as a sequence of entropic trust-region updates subject to dynamic constraints. This framework gives rise to a family of forward-backward algorithms, whose structure is determined by the chosen factorization of the variational posterior. By focusing on Gauss--Markov approximations, we derive recursive schemes with favorable computational complexity. For general nonlinear, non-Gaussian models we close the recursions using generalized statistical linear regression and Fourier--Hermite moment matching.

The problem of choosing appropriate values for missing data is often encountered in the data science. We describe a novel method containing both traditional mathematics and machine learning elements for prediction (imputation) of missing data. This method is based on the notion of distance between shifted linear subspaces representing the existing data and candidate sets. The existing data set is represented by the subspace spanned by its first principal components. Solutions for the case of the Euclidean metric are given.

The use of momentum in stochastic gradient methods has become a widespread practice in machine learning. Different variants of momentum, including heavy-ball momentum, Nesterov's accelerated gradient (NAG), and quasi-hyperbolic momentum (QHM), have demonstrated success on various tasks.

Via reduction, our new bound also implies improved bounds for strongly convex-concave and convex-concave minimax optimization problems.

's are the corresponding class labels.

It is obvious that Eq. (5) holds for k = 2 . The information of the datasets we used is shown in Table 1. The first four rows in Table 1 are the existing label distribution datasets; the last three rows in Table 1 are the datasets we created. Since some examples in the original label distribution datasets do not satisfy the prerequisites of our paper (i.e., there are some examples

End-to-end deep learning has achieved impressive results but remains limited by its reliance on large labeled datasets, poor generalization to unseen scenarios, and growing computational demands. In contrast, classical optimization methods are data-efficient and lightweight but often suffer from slow convergence. While learned optimizers offer a promising fusion of both worlds, most focus on first-order methods, leaving learned second-order approaches largely unexplored. We propose a novel learned second-order optimizer that introduces a trainable preconditioning unit to enhance the classical Symmetric-Rank-One (SR1) algorithm. This unit generates data-driven vectors used to construct positive semi-definite rank-one matrices, aligned with the secant constraint via a learned projection. Our method is evaluated through analytic experiments and on the real-world task of Monocular Human Mesh Recovery (HMR), where it outperforms existing learned optimization-based approaches. Featuring a lightweight model and requiring no annotated data or fine-tuning, our approach offers strong generalization and is well-suited for integration into broader optimization-based frameworks.