English
Related papers

Related papers: Adaptive Sampled Softmax with Inverted Multi-Index…

200 papers

Two-tower neural networks are a popular architecture for the retrieval stage in recommender systems. These models are typically trained with a softmax loss over the item catalog. However, in web-scale settings, the item catalog is often…

Information Retrieval · Computer Science 2025-07-29 Kirill Khrylchenko , Vladimir Baikalov , Sergei Makeev , Artem Matveev , Sergei Liamaev

Data selection is essential for training deep learning models. An effective data sampler assigns proper sampling probability for training data and helps the model converge to a good local minimum with high performance. Previous studies in…

Machine Learning · Computer Science 2024-10-10 Jiawei Yao , Chuming Li , Canran Xiao

While transformer models exhibit strong in-context learning (ICL) abilities, they often fail to generalize under simple distribution shifts. We analyze these failures and identify Softmax, the scoring function in the attention mechanism, as…

Computation and Language · Computer Science 2026-05-12 Omar Naim , Swarnadeep Bhar , Jérôme Bolte , Nicholas Asher

Randomized smoothing has emerged as a potent certifiable defense against adversarial attacks by employing smoothing noises from specific distributions to ensure the robustness of a smoothed classifier. However, the utilization of Monte…

Machine Learning · Computer Science 2025-04-01 Devansh Bhardwaj , Kshitiz Kaushik , Sarthak Gupta

We show that the variance of the Monte Carlo estimator that is importance sampled from an exponential family is a convex function of the natural parameter of the distribution. With this insight, we propose an adaptive importance sampling…

Methodology · Statistics 2015-01-12 Ernest K. Ryu , Stephen P. Boyd

We consider class incremental learning (CIL) problem, in which a learning agent continuously learns new classes from incrementally arriving training data batches and aims to predict well on all the classes learned so far. The main challenge…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Hongjoon Ahn , Jihwan Kwak , Subin Lim , Hyeonsu Bang , Hyojun Kim , Taesup Moon

In this work, we introduce a novel class of adaptive Monte Carlo methods, called adaptive independent sticky MCMC algorithms, for efficient sampling from a generic target probability density function (pdf). The new class of algorithms…

Computation · Statistics 2025-04-09 L. Martino , R. Casarin , F. Leisen , D. Luengo

This paper introduces self-paced task selection to multitask learning, where instances from more closely related tasks are selected in a progression of easier-to-harder tasks, to emulate an effective human education strategy, but applied to…

Machine Learning · Statistics 2017-06-20 Keerthiram Murugesan , Jaime Carbonell

Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks. The key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test…

Computer Vision and Pattern Recognition · Computer Science 2020-07-20 Chenghao Liu , Zhihao Wang , Doyen Sahoo , Yuan Fang , Kun Zhang , Steven C. H. Hoi

Converting an n-dimensional vector to a probability distribution over n objects is a commonly used component in many machine learning tasks like multiclass classification, multilabel classification, attention mechanisms etc. For this,…

We propose a new scalable multi-class Gaussian process classification approach building on a novel modified softmax likelihood function. The new likelihood has two benefits: it leads to well-calibrated uncertainty estimates and allows for…

Machine Learning · Statistics 2019-05-24 Théo Galy-Fajou , Florian Wenzel , Christian Donner , Manfred Opper

We introduce MADGRAD, a novel optimization method in the family of AdaGrad adaptive gradient methods. MADGRAD shows excellent performance on deep learning optimization problems from multiple fields, including classification and…

Machine Learning · Computer Science 2021-08-27 Aaron Defazio , Samy Jelassi

Adaptive importance sampling is a class of techniques for finding good proposal distributions for importance sampling. Often the proposal distributions are standard probability distributions whose parameters are adapted based on the…

Computation · Statistics 2021-03-10 Topi Paananen , Juho Piironen , Paul-Christian Bürkner , Aki Vehtari

Selecting a good column (or row) subset of massive data matrices has found many applications in data analysis and machine learning. We propose a new adaptive sampling algorithm that can be used to improve any relative-error column selection…

Data Structures and Algorithms · Computer Science 2015-10-15 Saurabh Paul , Malik Magdon-Ismail , Petros Drineas

Monte Carlo methods represent the "de facto" standard for approximating complicated integrals involving multidimensional target distributions. In order to generate random realizations from the target distribution, Monte Carlo techniques use…

Computation · Statistics 2022-01-21 L. Martino , V. Elvira , D. Luengo , J. Corander

Evaluating the log-sum-exp function or the softmax function is a key step in many modern data science algorithms, notably in inference and classification. Because of the exponentials that these functions contain, the evaluation is prone to…

Numerical Analysis · Mathematics 2019-09-10 Pierre Blanchard , Desmond J. Higham , Nicholas J. Higham

Despite achieving state-of-the-art results in nearly all Natural Language Processing applications, fine-tuning Transformer-based language models still requires a significant amount of labeled data to work. A well known technique to reduce…

Machine Learning · Computer Science 2025-03-13 Julius Gonsior , Christian Falkenberg , Silvio Magino , Anja Reusch , Maik Thiele , Wolfgang Lehner

The motivation for this paper stems from the desire to develop an adaptive sampling method for solving constrained optimization problems in which the objective function is stochastic and the constraints are deterministic. The method…

Optimization and Control · Mathematics 2021-01-01 Yuchen Xie , Raghu Bollapragada , Richard Byrd , Jorge Nocedal

Choosing the optimization algorithm that performs best on a given machine learning problem is often delicate, and there is no guarantee that current state-of-the-art algorithms will perform well across all tasks. Consequently, the more…

Optimization and Control · Mathematics 2024-06-25 Måns Williamson , Monika Eisenmann , Tony Stillfjord

Domain shifts are ubiquitous in machine learning, and can substantially degrade a model's performance when deployed to real-world data. To address this, distribution alignment methods aim to learn feature representations which are invariant…

Machine Learning · Computer Science 2024-10-08 Andrea Napoli , Paul White
‹ Prev 1 3 4 5 6 7 10 Next ›