English
Related papers

Related papers: Effectiveness of MPC-friendly Softmax Replacement

200 papers

Training a classifier over a large number of classes, known as 'extreme classification', has become a topic of major interest with applications in technology, science, and e-commerce. Traditional softmax regression induces a gradient cost…

Machine Learning · Statistics 2020-02-18 Robert Bamler , Stephan Mandt

The transformer neural network architecture uses a form of attention in which the dot product of query and key is divided by the square root of the key dimension before applying softmax. This scaling of the dot product is designed to avoid…

Machine Learning · Computer Science 2023-11-17 James Bernhard

We propose DropMax, a stochastic version of softmax classifier which at each iteration drops non-target classes according to dropout probabilities adaptively decided for each instance. Specifically, we overlay binary masking variables over…

Machine Learning · Computer Science 2018-11-05 Hae Beom Lee , Juho Lee , Saehoon Kim , Eunho Yang , Sung Ju Hwang

Binary neural networks leverage $\mathrm{Sign}$ function to binarize weights and activations, which require gradient estimators to overcome its non-differentiability and will inevitably bring gradient errors during backpropagation. Although…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Yefei He , Luoming Zhang , Weijia Wu , Hong Zhou

Representational similarity metrics typically force all units to be matched, making them susceptible to noise and outliers common in neural representations. We extend the soft-matching distance to a partial optimal transport setting that…

Machine Learning · Computer Science 2026-02-24 Chaitanya Kapoor , Alex H. Williams , Meenakshi Khosla

With an eye towards human-centered automation, we contribute to the development of a systematic means to infer features of human decision-making from behavioral data. Motivated by the common use of softmax selection in models of human…

Optimization and Control · Mathematics 2015-09-01 Paul Reverdy , Naomi E. Leonard

We provide a systematic recipe for translating ReLU approximation results to softmax attention mechanism. This recipe covers many common approximation targets. Importantly, it yields target-specific, economic resource bounds beyond…

Machine Learning · Computer Science 2026-04-29 Jerry Yao-Chieh Hu , Mingcheng Lu , Yi-Chen Lee , Han Liu

Within the framework of natural orbital functional theory, having a convenient representation of the occupation numbers and orbitals becomes critical for the computational performance of the calculations. Recognizing this, we propose an…

In order to push the performance on realistic computer vision tasks, the number of classes in modern benchmark datasets has significantly increased in recent years. This increase in the number of classes comes along with increased ambiguity…

Machine Learning · Statistics 2016-04-14 Maksim Lapin , Matthias Hein , Bernt Schiele

Categorical variables are a natural choice for representing discrete structure in the world. However, stochastic neural networks rarely use categorical latent variables due to the inability to backpropagate through samples. In this work, we…

Machine Learning · Statistics 2017-08-08 Eric Jang , Shixiang Gu , Ben Poole

This work aims to develop a measure that can accurately rank the performance of various classifiers when they are tested on unlabeled data from out-of-distribution (OOD) distributions. We commence by demonstrating that conventional…

Machine Learning · Computer Science 2024-06-17 Weijie Tu , Weijian Deng , Liang Zheng , Tom Gedeon

Neural Network (NN) classifiers can assign extreme probabilities to samples that have not appeared during training (out-of-distribution samples) resulting in erroneous and unreliable predictions. One of the causes for this unwanted…

Signal Processing · Electrical Eng. & Systems 2020-10-12 Niccolò Antonello , Philip N. Garner

Learning image representations on decentralized data can bring many benefits in cases where data cannot be aggregated across data silos. Softmax cross entropy loss is highly effective and commonly used for learning image representations.…

Machine Learning · Computer Science 2022-03-10 Sagar M. Waghmare , Hang Qi , Huizhong Chen , Mikhail Sirotenko , Tomer Meron

We empirically investigate the (negative) expected accuracy as an alternative loss function to cross entropy (negative log likelihood) for classification tasks. Coupled with softmax activation, it has small derivatives over most of its…

Machine Learning · Computer Science 2019-05-03 Ozan İrsoy

Large language models (LLMs) have brought significant changes to human society. Softmax regression and residual neural networks (ResNet) are two important techniques in deep learning: they not only serve as significant theoretical…

Machine Learning · Computer Science 2023-09-26 Zhao Song , Weixin Wang , Junze Yin

To protect multicores from soft-error perturbations, resiliency schemes have been developed with high coverage but high power and performance overheads. Emerging safety-critical machine learning applications are increasingly being deployed…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-07-11 Qingchuan Shi , Hamza Omar , Omer Khan

Neural networks (NNs) have been successfully deployed in various fields. In NNs, a large number of multiplyaccumulate (MAC) operations need to be performed. Most existing digital hardware platforms rely on parallel MAC units to accelerate…

Systems and Control · Electrical Eng. & Systems 2023-09-20 Kangwei Xu , Grace Li Zhang , Ulf Schlichtmann , Bing Li

Policy-gradient methods are widely used for learning control policies. They can be easily distributed to multiple workers and reach state-of-the-art results in many domains. Unfortunately, they exhibit large variance and subsequently suffer…

Machine Learning · Computer Science 2022-09-29 Gal Dalal , Assaf Hallak , Shie Mannor , Gal Chechik

Large and performant neural networks are often overparameterized and can be drastically reduced in size and complexity thanks to pruning. Pruning is a group of methods, which seeks to remove redundant or unnecessary weights or groups of…

Computer Vision and Pattern Recognition · Computer Science 2023-02-15 Robin Dupont , Mohammed Amine Alaoui , Hichem Sahbi , Alice Lebois

The $Q$-function is a central quantity in many Reinforcement Learning (RL) algorithms for which RL agents behave following a (soft)-greedy policy w.r.t. to $Q$. It is a powerful tool that allows action selection without a model of the…

Machine Learning · Computer Science 2022-06-01 Nino Vieillard , Marcin Andrychowicz , Anton Raichuk , Olivier Pietquin , Matthieu Geist