English
Related papers

Related papers: Learning and approximation capability of orthogona…

200 papers

The general theory of greedy approximation with respect to arbitrary dictionaries is well developed in the case of real Banach spaces. Recently, some of results proved for the Weak Chebyshev Greedy Algorithm (WCGA) in the case of real…

Functional Analysis · Mathematics 2024-10-01 A. Gasnikov , V. Temlyakov

In this paper we present the greedy step averaging(GSA) method, a parameter-free stochastic optimization algorithm for a variety of machine learning problems. As a gradient-based optimization method, GSA makes use of the information from…

Machine Learning · Computer Science 2016-11-14 Xiatian Zhang , Fan Yao , Yongjun Tian

In order to automate AI research we introduce a full, end-to-end framework, OMEGA: Optimizing Machine learning by Evaluating Generated Algorithms, that starts at idea generation and ends with executable code. Our system combines structured…

Artificial Intelligence · Computer Science 2026-04-30 Jeremy Nixon , Annika Singh

Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias can explain their lack of robustness out of distribution…

Machine Learning · Computer Science 2022-09-13 Damien Teney , Ehsan Abbasnejad , Simon Lucey , Anton van den Hengel

Optimal transport (OT) distances are finding evermore applications in machine learning and computer vision, but their wide spread use in larger-scale problems is impeded by their high computational cost. In this work we develop a family of…

Machine Learning · Statistics 2018-03-06 Brahim Khalil Abid , Robert M. Gower

We give a new separation result between the generalization performance of stochastic gradient descent (SGD) and of full-batch gradient descent (GD) in the fundamental stochastic convex optimization model. While for SGD it is well-known that…

Machine Learning · Computer Science 2021-07-01 Idan Amir , Tomer Koren , Roi Livni

In Continual Learning settings, deep neural networks are prone to Catastrophic Forgetting. Orthogonal Gradient Descent was proposed to tackle the challenge. However, no theoretical guarantees have been proven yet. We present a theoretical…

Machine Learning · Statistics 2020-12-07 Mehdi Abbana Bennani , Thang Doan , Masashi Sugiyama

This paper describes a simple greedy D-approximation algorithm for any covering problem whose objective function is submodular and non-decreasing, and whose feasible region can be expressed as the intersection of arbitrary (closed upwards)…

Data Structures and Algorithms · Computer Science 2015-06-02 Christos Koufogiannakis , Neal E. Young

In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a…

Machine Learning · Statistics 2018-12-27 Lam M. Nguyen , Nam H. Nguyen , Dzung T. Phan , Jayant R. Kalagnanam , Katya Scheinberg

Many modern learning tasks involve fitting nonlinear models to data which are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Due to this overparameterization, the training…

Machine Learning · Computer Science 2018-12-27 Samet Oymak , Mahdi Soltanolkotabi

One-class learning (OCL) comprises a set of techniques applied when real-world problems have a single class of interest. The usual procedure for OCL is learning a hypersphere that comprises instances of this class and, ideally, repels…

Machine Learning · Computer Science 2024-08-27 M. P. S. Gôlo , J. G. B. M. Junior , D. F. Silva , R. M. Marcacini

This paper establishes theoretical bonafides for implicit concurrent multivariate effect evaluation--implicit concurrency for short---a broad and versatile computational learning efficiency thought to underlie general-purpose, non-local,…

Neural and Evolutionary Computing · Computer Science 2013-07-16 Keki M. Burjorjee

In this work we introduce a new optimisation method called SAGA in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA improves on the theory behind SAG…

Machine Learning · Computer Science 2014-12-17 Aaron Defazio , Francis Bach , Simon Lacoste-Julien

Orthogonal Gradient Descent (OGD) has emerged as a powerful method for continual learning. However, its Euclidean projections do not leverage the underlying information-geometric structure of the problem, which can lead to suboptimal…

Machine Learning · Computer Science 2025-12-09 Yajat Yadav , Patrick Mendoza , Jathin Korrapati

We investigate the Randomized Stochastic Accelerated Gradient (RSAG) method, utilizing either constant or adaptive step sizes, for stochastic optimization problems with generalized smooth objective functions. Under relaxed affine variance…

Optimization and Control · Mathematics 2025-02-25 Chenhao Yu , Yusu Hong , Junhong Lin

The inductive bias of a neural network is largely determined by the architecture and the training algorithm. To achieve good generalization, how to effectively train a neural network is of great importance. We propose a novel orthogonal…

Machine Learning · Computer Science 2021-06-08 Weiyang Liu , Rongmei Lin , Zhen Liu , James M. Rehg , Liam Paull , Li Xiong , Le Song , Adrian Weller

Optimizing non-convex functions is a fundamental challenge across machine learning and combinatorial optimization. We introduce and study $\gamma$-weakly $\theta$-up-concavity, a novel first-order condition that characterizes a broad class…

Machine Learning · Computer Science 2026-05-11 Mohammad Pedramfar , Vaneet Aggarwal

In online learning an algorithm plays against an environment with losses possibly picked by an adversary at each round. The generality of this framework includes problems that are not adversarial, for example offline optimization, or saddle…

Machine Learning · Computer Science 2021-02-04 Ryan D'Orazio , Ruitong Huang

We consider a broad class of first-order optimization algorithms which are \emph{oblivious}, in the sense that their step sizes are scheduled regardless of the function under consideration, except for limited side-information such as…

Optimization and Control · Mathematics 2016-05-12 Yossi Arjevani , Ohad Shamir

The main goal of this paper is twofold. First, we extend some results known in the case of weak greedy algorithms with a scalar parameter to the case of weak greedy algorithms with a weakness sequence. Second, we formulate a new setting of…

Numerical Analysis · Mathematics 2026-04-30 A. S. Spivak , V. N. Temlyakov