English
Related papers

Related papers: Convergence of First-Order Algorithms for Meta-Lea…

200 papers

In this paper, we study optimization methods consisting of iteratively minimizing surrogates of an objective function. By proposing several algorithmic variants and simple convergence analyses, we make two main contributions. First, we…

Machine Learning · Statistics 2013-05-15 Julien Mairal

In this paper we consider minimization of a difference-of-convex (DC) function with and without linear constraints. We first study a smooth approximation of a generic DC function, termed difference-of-Moreau-envelopes (DME) smoothing, where…

Optimization and Control · Mathematics 2022-11-21 Kaizhao Sun , Xu Andy Sun

Deep learning typically requires large data sets and much compute power for each new problem that is learned. Meta-learning can be used to learn a good prior that facilitates quick learning, thereby relaxing these requirements so that new…

Machine Learning · Computer Science 2022-11-08 Mike Huisman , Aske Plaat , Jan N. van Rijn

Modern large-scale statistical models require to estimate thousands to millions of parameters. This is often accomplished by iterative algorithms such as gradient descent, projected gradient descent or their accelerated versions. What are…

Machine Learning · Statistics 2020-03-04 Michael Celentano , Andrea Montanari , Yuchen Wu

We consider the minimization of submodular functions subject to ordering constraints. We show that this optimization problem can be cast as a convex optimization problem on a space of uni-dimensional measures, with ordering constraints…

Machine Learning · Computer Science 2017-07-31 Francis Bach

We study bilevel optimization problems where the lower-level problems are strongly convex and have coupled linear constraints. To overcome the potential non-smoothness of the hyper-objective and the computational challenges associated with…

Optimization and Control · Mathematics 2026-02-06 Wei Shen , Jiawei Zhang , Minhui Huang , Cong Shen

Recent work has shown that stochastically perturbed gradient methods can efficiently escape strict saddle points of smooth functions. We extend this body of work to nonsmooth optimization, by analyzing an inexact analogue of a…

Optimization and Control · Mathematics 2021-06-21 Damek Davis , Mateo Díaz , Dmitriy Drusvyatskiy

Continuous DR-submodular functions are a class of functions that satisfy the Diminishing Returns (DR) property, which implies that they are concave along non-negative directions. Existing works have studied monotone continuous DR-submodular…

Machine Learning · Computer Science 2022-05-31 Omid Sadeghi , Maryam Fazel

Model Agnostic Meta Learning (MAML) is widely used to find a good initialization for a family of tasks. Despite its success, a critical challenge in MAML is to calculate the gradient w.r.t. the initialization of a long training trajectory…

Machine Learning · Computer Science 2023-02-27 Shibo Li , Zheng Wang , Akil Narayan , Robert Kirby , Shandian Zhe

Recently, Arjevani et al. [1] established a lower bound of iteration complexity for the first-order optimization under an $L$-smooth condition and a bounded noise variance assumption. However, a thorough review of existing literature on…

Machine Learning · Computer Science 2023-10-30 Bohan Wang , Jingwen Fu , Huishuai Zhang , Nanning Zheng , Wei Chen

In this paper, we propose first-order feasible methods for difference-of-convex (DC) programs with smooth inequality and simple geometric constraints. Our strategy for maintaining feasibility of the iterates is based on a "retraction" idea…

Optimization and Control · Mathematics 2022-12-05 Yongle Zhang , Guoyin Li , Ting Kei Pong , Shiqi Xu

We study the setting of \emph{performative reinforcement learning} where the deployed policy affects both the reward, and the transition of the underlying Markov decision process. Prior work~\parencite{MTR23} has addressed this problem…

Machine Learning · Computer Science 2025-03-18 Debmalya Mandal , Goran Radanovic

Magnetic Resonance (MR) images suffer from various types of artifacts due to motion, spatial resolution, and under-sampling. Conventional deep learning methods deal with removing a specific type of artifact, leading to separately trained…

Image and Video Processing · Electrical Eng. & Systems 2023-04-14 Arun Palla , Sriprabha Ramanarayanan , Keerthi Ram , Mohanasankar Sivaprakasam

First-order operator splitting methods are ubiquitous among many fields through science and engineering, such as inverse problems, signal/image processing, statistics, data science and machine learning, to name a few. In this paper, we…

Optimization and Control · Mathematics 2020-09-10 Clarice Poon , Jingwei Liang

We present an approach to obtain convergence guarantees of optimization algorithms for deep networks based on elementary arguments and computations. The convergence analysis revolves around the analytical and computational structures of…

Machine Learning · Computer Science 2021-01-01 Vincent Roulet , Zaid Harchaoui

Meta-learning, or "learning to learn," aims to enable models to quickly adapt to new tasks with minimal data. While traditional methods like Model-Agnostic Meta-Learning (MAML) optimize parameters in Euclidean space, they often struggle to…

Machine Learning · Computer Science 2025-03-17 JuneYoung Park , YuMi Lee , Tae-Joon Kim , Jang-Hwan Choi

We present a primal-dual algorithmic framework to obtain approximate solutions to a prototypical constrained convex optimization problem, and rigorously characterize how common structural assumptions affect the numerical efficiency. Our…

Optimization and Control · Mathematics 2015-03-04 Quoc Tran-Dinh , Volkan Cevher

In this paper, we study the generalization properties of Model-Agnostic Meta-Learning (MAML) algorithms for supervised learning problems. We focus on the setting in which we train the MAML model over $m$ tasks, each with $n$ data points,…

Machine Learning · Computer Science 2021-11-18 Alireza Fallah , Aryan Mokhtari , Asuman Ozdaglar

Higher-order tensor methods were recently proposed for minimizing smooth convex and nonconvex functions. Higher-order algorithms accelerate the convergence of the classical first-order methods thanks to the higher-order derivatives used in…

Optimization and Control · Mathematics 2024-01-11 Ion Necoara

It has been shown that many first-order methods satisfy the perturbed Fenchel duality inequality, which yields a unified derivation of convergence. More first-order methods are discussed in this paper, e.g., dual averaging and bundle…

Optimization and Control · Mathematics 2024-12-04 Tiantian Zhao