English
Related papers

Related papers: Debiasing Mini-Batch Quadratics for Applications i…

200 papers

The goal of metric learning is to learn a function that maps samples to a lower-dimensional space where similar samples lie closer than dissimilar ones. Particularly, deep metric learning utilizes neural networks to learn such a mapping.…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Jenny Seidenschwarz , Ismail Elezi , Laura Leal-Taixé

Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suffers from the requirements of additional network components…

Machine Learning · Computer Science 2019-10-23 Dongmin Park , Seokil Hong , Bohyung Han , Kyoung Mu Lee

Deep probabilistic time series forecasting has gained attention for its ability to provide nonlinear approximation and valuable uncertainty quantification for decision-making. However, existing models often oversimplify the problem by…

Machine Learning · Statistics 2024-10-22 Vincent Zhihao Zheng , Seongjin Choi , Lijun Sun

Using backward error analysis, we compute implicit training biases in multitask and continual learning settings for neural networks trained with stochastic gradient descent. In particular, we derive modified losses that are implicitly…

Machine Learning · Statistics 2023-11-02 Benoit Dherin

Sequential quadratic optimization algorithms are proposed for solving smooth nonlinear optimization problems with equality constraints. The main focus is an algorithm proposed for the case when the constraint functions are deterministic,…

Optimization and Control · Mathematics 2020-07-22 Albert Berahas , Frank E. Curtis , Daniel P. Robinson , Baoyu Zhou

We study stochastic Cubic Newton methods for solving general possibly non-convex minimization problems. We propose a new framework, which we call the helper framework, that provides a unified view of the stochastic and variance-reduced…

Optimization and Control · Mathematics 2025-12-19 El Mahdi Chayti , Nikita Doikov , Martin Jaggi

Matrices arising in scientific applications frequently admit linear low-rank approximations due to smoothness in the physical and/or temporal domain of the problem. In large-scale problems, computing an optimal low-rank approximation can be…

Numerical Analysis · Mathematics 2021-05-05 Alec Michael Dunton , Alireza Doostan

In this work, we investigate a particular class of shape optimization problems under uncertainties on the input parameters. More precisely, we are interested in the minimization of the expectation of a quadratic objective in a situation…

Optimization and Control · Mathematics 2015-06-01 M. Dambrine , C. Dapogny , H. Harbrecht

Binary quadratic programming problems have attracted much attention in the last few decades due to their potential applications. This type of problems are NP-hard in general, and still considered a challenge in the design of efficient…

Data Structures and Algorithms · Computer Science 2014-11-20 Khaled Elbassioni , Trung Thanh Nguyen

Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns. In this work, we study how the critical batch size changes based on…

Variational inequalities represent a broad class of problems, including minimization and min-max problems, commonly found in machine learning. Existing second-order and high-order methods for variational inequalities require precise…

Uncertainty quantification is an important and challenging problem in deep learning. Previous methods rely on dropout layers which are not present in modern deep architectures or batch normalization which is sensitive to batch sizes. In…

Computer Vision and Pattern Recognition · Computer Science 2020-07-10 Lukasz Wandzik , Raul Vicente Garcia , Jörg Krüger

Discrete optimization problems often arise in deep learning tasks, despite the fact that neural networks typically operate on continuous data. One class of these problems involve objective functions which depend on neural networks, but…

Machine Learning · Computer Science 2023-10-17 Eric Lei , Arman Adibi , Hamed Hassani

Neural ordinary differential equations (ODEs) are an emerging class of deep learning models for dynamical systems. They are particularly useful for learning an ODE vector field from observed trajectories (i.e., inverse problems). We here…

Machine Learning · Computer Science 2023-05-23 Katharina Ott , Michael Tiemann , Philipp Hennig

With limited high-quality data and growing compute, multi-epoch training is gaining back its importance across sub-areas of deep learning. Adam(W), versions of which are go-to optimizers for many tasks such as next token prediction, has two…

Machine Learning · Computer Science 2026-05-11 Matias D. Cattaneo , Boris Shigida

Metric learning is a fundamental problem in computer vision whereby a model is trained to learn a semantically useful embedding space via ranking losses. Traditionally, the effectiveness of a ranking loss depends on the minibatch size, and…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Thalaiyasingam Ajanthan , Matt Ma , Anton van den Hengel , Stephen Gould

Deep neural networks achieve impressive results across diverse applications, yet their overconfidence on unseen inputs necessitates reliable epistemic uncertainty modelling. Existing methods for uncertainty modelling face a fundamental…

Machine Learning · Computer Science 2026-05-04 Yao Ni , Jeremie Houssineau , Yew Soon Ong , Piotr Koniusz

Deep learning has seen remarkable developments over the last years, many of them inspired by neuroscience. However, the main learning mechanism behind these advances - error backpropagation - appears to be at odds with neurobiology. Here,…

Neurons and Cognition · Quantitative Biology 2018-10-29 João Sacramento , Rui Ponte Costa , Yoshua Bengio , Walter Senn

This paper focuses on regularisation methods using models up to the third order to search for up to second-order critical points of a finite-sum minimisation problem. The variant presented belongs to the framework of [3]: it employs random…

Numerical Analysis · Mathematics 2021-04-05 Stefania Bellavia , Gianmarco Gurioli , Benedetta Morini , Philippe L. Toint

Active learning parallelization is widely used, but typically relies on fixing the batch size throughout experimentation. This fixed approach is inefficient because of a dynamic trade-off between cost and speed -- larger batches are more…

Machine Learning · Computer Science 2024-10-15 Masaki Adachi , Satoshi Hayakawa , Martin Jørgensen , Xingchen Wan , Vu Nguyen , Harald Oberhauser , Michael A. Osborne