English
Related papers

Related papers: Unpacking Softmax: How Temperature Drives Represen…

200 papers

In replay-based methods for continual learning, replaying input samples in episodic memory has shown its effectiveness in alleviating catastrophic forgetting. However, the potential key factor of cross-entropy loss with softmax in causing…

Machine Learning · Computer Science 2024-01-25 Hoyong Kim , Minchan Kwon , Kangil Kim

The development of deep learning algorithms has extensively empowered humanity's task automatization capacity. However, the huge improvement in the performance of these models is highly correlated with their increasing level of complexity,…

Computer Vision and Pattern Recognition · Computer Science 2024-01-19 Eduarda Caldeira , Pedro C. Neto , Marco Huber , Naser Damer , Ana F. Sequeira

We study transformer language models, analyzing attention heads whose attention patterns are spread out, and whose attention scores depend weakly on content. We argue that the softmax denominators of these heads are stable when the…

Computation and Language · Computer Science 2025-10-07 Alex Gibson

Performative prediction is a framework for learning models that influence the data they intend to predict. We focus on finding classifiers that are performatively stable, i.e. optimal for the data distribution they induce. Standard…

Machine Learning · Computer Science 2025-02-07 Mehrnaz Mofakhami , Ioannis Mitliagkas , Gauthier Gidel

The softmax loss and its variants are widely used as objectives for embedding learning, especially in applications like face recognition. However, the intra- and inter-class objectives in the softmax loss are entangled, therefore a…

Computer Vision and Pattern Recognition · Computer Science 2020-02-13 Lanqing He , Zhongdao Wang , Yali Li , Shengjin Wang

Intra-class compactness and inter-class separability are crucial indicators to measure the effectiveness of a model to produce discriminative features, where intra-class compactness indicates how close the features with the same label are…

Computer Vision and Pattern Recognition · Computer Science 2019-07-16 Yan Luo , Yongkang Wong , Mohan Kankanhalli , Qi Zhao

Decoding in large language models is often described as scoring tokens and normalizing with softmax. We give a minimal, self-contained account of this step as a constrained variational principle on the probability simplex. The discrete,…

Machine Learning · Computer Science 2025-09-01 Christopher R. Lee-Jenkins

Decomposing a deep neural network's learned representations into interpretable features could greatly enhance its safety and reliability. To better understand features, we adopt a geometric perspective, viewing them as a learned coordinate…

Machine Learning · Computer Science 2025-04-30 Aryeh Brill

In deep learning, transferring information from a pretrained network to a downstream task by finetuning has many benefits. The choice of task head plays an important role in fine-tuning, as the pretrained and downstream tasks are usually…

Machine Learning · Computer Science 2023-02-14 Yi Ren , Shangmin Guo , Wonho Bae , Danica J. Sutherland

Transformers can perform in-context classification from a few labeled examples, yet the inference-time algorithm remains opaque. We study multi-class linear classification in the hard no-margin regime and make the computation identifiable…

Machine Learning · Computer Science 2026-04-20 Patrick Lutz , Themistoklis Haris , Arjun Chandra , Aditya Gangrade , Venkatesh Saligrama

In naturalistic learning problems, a model's input contains a wide range of features, some useful for the task at hand, and others not. Of the useful features, which ones does the model use? Of the task-irrelevant features, which ones does…

Machine Learning · Computer Science 2020-10-26 Katherine L. Hermann , Andrew K. Lampinen

Top-K sparse softmax gating mixture of experts has been widely used for scaling up massive deep-learning architectures without increasing the computational cost. Despite its popularity in real-world applications, the theoretical…

Machine Learning · Statistics 2024-02-27 Huy Nguyen , Pedram Akbarian , Fanqi Yan , Nhat Ho

The sampling temperature, a critical hyperparameter in large language models (LLMs), modifies the logits before the softmax layer, thereby reshaping the distribution of output tokens. Recent studies have challenged the Stochastic Parrots…

Computation and Language · Computer Science 2025-06-10 Lujun Li , Lama Sleem , Niccolo' Gentile , Geoffrey Nichil , Radu State

We provide two characterizations, one axiomatic and the other neuro-computational, of the dependence of choice probabilities on deadlines, within the widely used softmax representation \[ p_{t}\left( a,A\right) =\dfrac{e^{\frac{u\left(…

Theoretical Economics · Economics 2021-01-28 Simone Cerreia-Vioglio , Fabio Maccheroni , Massimo Marinacci , Aldo Rustichini

Large transformer models have achieved state-of-the-art results in numerous natural language processing tasks. Among the pivotal components of the transformer architecture, the attention mechanism plays a crucial role in capturing token…

Computation and Language · Computer Science 2026-03-16 Yichuan Deng , Zhao Song , Kaijun Yuan , Tianyi Zhou

Transformers have achieved remarkable success in several domains, ranging from natural language processing to computer vision. Nevertheless, it has been recently shown that stacking self-attention layers - the distinctive architectural…

Machine Learning · Computer Science 2022-06-08 Lorenzo Noci , Sotiris Anagnostidis , Luca Biggio , Antonio Orvieto , Sidak Pal Singh , Aurelien Lucchi

Regularization is crucial to the success of many practical deep learning models, in particular in a more often than not scenario where there are only a few to a moderate number of accessible training samples. In addition to weight decay,…

Machine Learning · Computer Science 2018-08-07 Che-Wei Huang , Shrikanth S. Narayanan

Datasets such as images, text, or movies are embedded in high-dimensional spaces. However, in important cases such as images of objects, the statistical structure in the data constrains samples to a manifold of dramatically lower…

Machine Learning · Computer Science 2019-10-29 Stefano Recanatesi , Matthew Farrell , Madhu Advani , Timothy Moore , Guillaume Lajoie , Eric Shea-Brown

Transformers have recently revolutionized many domains in modern machine learning and one salient discovery is their remarkable in-context learning capability, where models can solve an unseen task by utilizing task-specific prompts without…

Machine Learning · Computer Science 2023-10-10 Yu Huang , Yuan Cheng , Yingbin Liang

Deep learning algorithms are well-known to have a propensity for fitting the training data very well and often fit even outliers and mislabeled data points. Such fitting requires memorization of training data labels, a phenomenon that has…

Machine Learning · Computer Science 2020-08-11 Vitaly Feldman , Chiyuan Zhang
‹ Prev 1 8 9 10 Next ›