English
Related papers

Related papers: NDCG-Consistent Softmax Approximation with Acceler…

200 papers

Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typically used with function approximation. In this setting, the…

We present ADMM-Softmax, an alternating direction method of multipliers (ADMM) for solving multinomial logistic regression (MLR) problems. Our method is geared toward supervised classification tasks with many examples and features. It…

Machine Learning · Computer Science 2019-07-12 Samy Wu Fung , Sanna Tyrväinen , Lars Ruthotto , Eldad Haber

Large language models (LLMs), such as ChatGPT and GPT4, have shown outstanding performance in many human life task. Attention computation plays an important role in training LLMs. Softmax unit and ReLU unit are the key structure in…

Machine Learning · Computer Science 2023-08-17 Yichuan Deng , Zhao Song , Shenghao Xie

Deep metric learning applied to various applications has shown promising results in identification, retrieval and recognition. Existing methods often do not consider different granularity in visual similarity. However, in many domain…

Computer Vision and Pattern Recognition · Computer Science 2021-05-17 Dipu Manandhar , Muhammet Bastan , Kim-Hui Yap

Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been…

Machine Learning · Statistics 2016-03-03 Oren Rippel , Manohar Paluri , Piotr Dollar , Lubomir Bourdev

In designing personalized ranking algorithms, it is desirable to encourage a high precision at the top of the ranked list. Existing methods either seek a smooth convex surrogate for a non-smooth ranking metric or directly modify updating…

Machine Learning · Statistics 2018-08-15 Kuan Liu , Prem Natarajan

In forming learning objectives, one oftentimes needs to aggregate a set of individual values to a single output. Such cases occur in the aggregate loss, which combines individual losses of a learning model over each training sample, and in…

Machine Learning · Computer Science 2022-04-05 Shu Hu , Yiming Ying , Xin Wang , Siwei Lyu

Learning distributed representations, or embeddings, that encode the relational similarity patterns among objects is a relevant task in machine learning. A popular method to learn the embedding matrices $X, Y$ is optimizing a loss function…

Machine Learning · Computer Science 2025-06-03 Lorenzo Dall'Amico , Enrico Maria Belliardo

Researches using margin based comparison loss demonstrate the effectiveness of penalizing the distance between face feature and their corresponding class centers. Despite their popularity and excellent performance, they do not explicitly…

Computer Vision and Pattern Recognition · Computer Science 2020-06-12 Ying Huang , Shangfeng Qiu , Wenwei Zhang , Xianghui Luo , Jinzhuo Wang

Previous work shows that adversarially robust generalization requires larger sample complexity, and the same dataset, e.g., CIFAR-10, which enables good standard accuracy may not suffice to train robust models. Since collecting new training…

Machine Learning · Computer Science 2020-02-21 Tianyu Pang , Kun Xu , Yinpeng Dong , Chao Du , Ning Chen , Jun Zhu

While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…

Machine Learning · Computer Science 2026-02-03 Mingwei Xu , Xuan Lin , Xinnan Guo , Wanqing Xu , Wanyun Cui

Training neural networks requires optimizing a loss function that may be highly irregular, and in particular neither convex nor smooth. Popular training algorithms are based on stochastic gradient descent with momentum (SGDM), for which…

Machine Learning · Computer Science 2026-03-17 Qinzi Zhang , Ashok Cutkosky

Loss functions play a key role in training superior deep neural networks. In convolutional neural networks (CNNs), the popular cross entropy loss together with softmax does not explicitly guarantee minimization of intra-class variance or…

Computer Vision and Pattern Recognition · Computer Science 2019-04-26 XiaoBin Li , WeiQiang Wang

Stochastic first-order methods for empirical risk minimization employ gradient approximations based on sampled data in lieu of exact gradients. Such constructions introduce noise into the learning dynamics, which can be corrected through…

Machine Learning · Computer Science 2025-03-18 Sean Xiao , Sangwoo Park , Stefan Vlaski

Multi-agent robust reinforcement learning, also known as multi-player robust Markov games (RMGs), is a crucial framework for modeling competitive interactions under environmental uncertainties, with wide applications in multi-agent systems.…

Machine Learning · Computer Science 2024-12-31 Yuchen Jiao , Gen Li

Semidefinite Programming (SDP) and Sums-of-Squares (SOS) relaxations have led to certifiably optimal non-minimal solvers for several robotics and computer vision problems. However, most non-minimal solvers rely on least-squares…

Computer Vision and Pattern Recognition · Computer Science 2020-06-15 Heng Yang , Pasquale Antonante , Vasileios Tzoumas , Luca Carlone

As the parameters of Large Language Models (LLMs) have scaled to hundreds of billions, the demand for efficient training methods -- balancing faster computation and reduced memory usage without sacrificing accuracy -- has become more…

Machine Learning · Computer Science 2025-03-03 Kaan Ozkara , Tao Yu , Youngsuk Park

We propose an online learning algorithm for a class of machine learning models under a separable stochastic approximation framework. The essence of our idea lies in the observation that certain parameters in the models are easier to…

Machine Learning · Computer Science 2023-05-23 Min Gan , Xiang-xiang Su , Guang-yong Chen , Jing Chen

Semi-supervised learning (SSL) has played an important role in leveraging unlabeled data when labeled data is limited. One of the most successful SSL approaches is based on consistency regularization, which encourages the model to produce…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Trung Q. Tran , Mingu Kang , Daeyoung Kim

Many problems in robotics, such as estimating the state from noisy sensor data or aligning two point clouds, can be posed and solved as least-squares problems. Unfortunately, vanilla nonminimal solvers for least-squares problems are…

Robotics · Computer Science 2024-07-31 Kyungmin Jung , Thomas Hitchcox , James Richard Forbes