English
Related papers

Related papers: Beyond Softmax: A Natural Parameterization for Cat…

200 papers

Deep multitask networks, in which one neural network produces multiple predictive outputs, can offer better speed and performance than their single-task counterparts but are challenging to train properly. We present a gradient normalization…

Computer Vision and Pattern Recognition · Computer Science 2018-07-16 Zhao Chen , Vijay Badrinarayanan , Chen-Yu Lee , Andrew Rabinovich

How to train deep neural networks (DNNs) to generalize well is a central concern in deep learning, especially for severely overparameterized networks nowadays. In this paper, we propose an effective method to improve the model…

Machine Learning · Computer Science 2022-06-28 Yang Zhao , Hao Zhang , Xiuyuan Hu

Standard deep learning architectures used for classification generate label predictions with a projection head and softmax activation function. Although successful, these methods fail to leverage the relational information between samples…

Machine Learning · Computer Science 2025-12-10 Jason Brown , Bohan Chen , Harris Hardiman-Mostow , Jeff Calder , Andrea L. Bertozzi

Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical inference. We propose Shortcut-Aware Reasoning Training (SART), a…

Computation and Language · Computer Science 2026-03-24 Hongyu Cao , Kunpeng Liu , Dongjie Wang , Yanjie Fu

The softmax activation function plays a crucial role in the success of large language models (LLMs), particularly in the self-attention mechanism of the widely adopted Transformer architecture. However, the underlying learning dynamics that…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Yingyu Liang , Zhenmei Shi , Zhao Song

Gradient-based iterative optimization methods are the workhorse of modern machine learning. They crucially rely on careful tuning of parameters like learning rate and momentum. However, one typically sets them using heuristic approaches…

Machine Learning · Computer Science 2025-12-05 Dravyansh Sharma

Normalization methods improve both optimization and generalization of ConvNets. To further boost performance, the recently-proposed switchable normalization (SN) provides a new perspective for deep learning: it learns to select different…

Computer Vision and Pattern Recognition · Computer Science 2019-03-12 Wenqi Shao , Tianjian Meng , Jingyu Li , Ruimao Zhang , Yudian Li , Xiaogang Wang , Ping Luo

Gradient descent can be surprisingly good at optimizing deep neural networks without overfitting and without explicit regularization. We find that the discrete steps of gradient descent implicitly regularize models by penalizing gradient…

Machine Learning · Computer Science 2022-07-20 David G. T. Barrett , Benoit Dherin

This paper considers policy search in continuous state-action reinforcement learning problems. Typically, one computes search directions using a classic expression for the policy gradient called the Policy Gradient Theorem, which decomposes…

Machine Learning · Computer Science 2020-04-13 Sujay Bhatt , Alec Koppel , Vikram Krishnamurthy

Deep neural networks are a promising approach towards multi-task learning because of their capability to leverage knowledge across domains and learn general purpose representations. Nevertheless, they can fail to live up to these promises…

Machine Learning · Computer Science 2019-12-17 Mihai Suteu , Yike Guo

Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Zhuotao Tian , Jiequan Cui , Li Jiang , Xiaojuan Qi , Xin Lai , Yixin Chen , Shu Liu , Jiaya Jia

Real-world data often follows a long-tailed distribution, which makes the performance of existing classification algorithms degrade heavily. A key issue is that samples in tail categories fail to depict their intra-class diversity. Humans…

Computer Vision and Pattern Recognition · Computer Science 2022-02-14 Xiaohua Chen , Yucan Zhou , Dayan Wu , Wanqian Zhang , Yu Zhou , Bo Li , Weiping Wang

In deep learning-based classification tasks, the softmax function's temperature parameter $T$ critically influences the output distribution and overall performance. This study presents a novel theoretical insight that the optimal…

Machine Learning · Computer Science 2026-04-24 Tatsuhito Hasegawa , Shunsuke Sakai

Neural collapse (NC) describes the structured geometry that emerges in the features and weights of trained classifiers. Recent theory suggests NC can be suboptimal in deep architectures, attributing this to an explicit low-rank bias from L2…

Machine Learning · Computer Science 2026-05-25 Connall Garrod , Jonathan P. Keating , Christos Thrampoulidis

Performative learning addresses the increasingly pervasive situations in which algorithmic decisions may induce changes in the data distribution as a consequence of their public deployment. We propose a novel view in which these…

Machine Learning · Computer Science 2024-11-05 Edwige Cyffers , Muni Sreenivas Pydi , Jamal Atif , Olivier Cappé

Neural implicit shape representations are an emerging paradigm that offers many potential benefits over conventional discrete representations, including memory efficiency at a high spatial resolution. Generalizing across shapes with such…

Computer Vision and Pattern Recognition · Computer Science 2020-06-18 Vincent Sitzmann , Eric R. Chan , Richard Tucker , Noah Snavely , Gordon Wetzstein

Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during…

Machine Learning · Statistics 2018-06-15 Yoonho Lee , Seungjin Choi

Categorical regressor variables are usually handled by introducing a set of indicator variables, and imposing a linear constraint to ensure identifiability in the presence of an intercept, or equivalently, using one of various coding…

Computation · Statistics 2018-05-21 Felicitas J. Detmer , Martin Slawski

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Wei Hu , Yuping Luo

Softmax is widely used in deep learning to map some representation to a probability distribution. As it is based on exp/log functions that are relatively expensive in multi-party computation, Mohassel and Zhang (2017) proposed a simpler…

Machine Learning · Computer Science 2021-07-07 Marcel Keller , Ke Sun