English
Related papers

Related papers: Disentangling Feature Structure: A Mathematically …

200 papers

This paper introduces a high-order Markov chain task to investigate how transformers learn to integrate information from multiple past positions with varying statistical significance. We demonstrate that transformers learn this task…

Machine Learning · Computer Science 2026-02-24 Oğuz Kaan Yüksel , Rodrigo Alvarez Lucendo , Nicolas Flammarion

We consider the task of building compact deep learning pipelines suitable for deployment on storage and power constrained mobile devices. We propose a unified framework to learn a broad family of structured parameter matrices that are…

Machine Learning · Statistics 2015-10-07 Vikas Sindhwani , Tara N. Sainath , Sanjiv Kumar

Transformers pretrained via next token prediction learn to factor their world into parts, representing these factors in orthogonal subspaces of the residual stream. We formalize two representational hypotheses: (1) a representation in the…

Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Qi Wang , Zhipeng Zhang , Baao Xie , Xin Jin , Yunbo Wang , Shiyu Wang , Liaomo Zheng , Xiaokang Yang , Wenjun Zeng

At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto-regressive objectives is closely related to…

Recent work has demonstrated the ability to leverage or distill pre-trained 2D features obtained using large pre-trained 2D models into 3D features, enabling impressive 3D editing and understanding capabilities using only 2D supervision.…

Computer Vision and Pattern Recognition · Computer Science 2025-02-21 Yoel Levy , David Shavin , Itai Lang , Sagie Benaim

Most stochastic gradient descent algorithms can optimize neural networks that are sub-differentiable in their parameters; however, this implies that the neural network's activation function must exhibit a degree of continuity which limits…

Neural and Evolutionary Computing · Computer Science 2021-12-16 Anastasis Kratsios , Behnoosh Zamanlooy

Transformers have become the dominant architecture for natural language processing. Part of their success is owed to a remarkable capability known as in-context learning (ICL): they can acquire and apply novel associations solely from their…

Artificial Intelligence · Computer Science 2026-01-12 Tiberiu Musat , Tiago Pimentel , Lorenzo Noci , Alessandro Stolfo , Mrinmaya Sachan , Thomas Hofmann

Deep imitation learning is promising for solving dexterous manipulation tasks because it does not require an environment model and pre-programmed robot behavior. However, its application to dual-arm manipulation tasks remains challenging.…

Robotics · Computer Science 2025-05-23 Heecheol Kim , Yoshiyuki Ohmura , Yasuo Kuniyoshi

Probabilistic generative models provide a flexible and systematic framework for learning the underlying geometry of data. However, model selection in this setting is challenging, particularly when selecting for ill-defined qualities such as…

Machine Learning · Computer Science 2022-10-05 Chester Holtz , Gal Mishne , Alexander Cloninger

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

Sentence and word embeddings encode structural and semantic information in a distributed manner. Part of the information encoded -- particularly lexical information -- can be seen as continuous, whereas other -- like structural information…

Computation and Language · Computer Science 2023-12-19 Vivi Nastase , Paola Merlo

Syntax is usually studied in the realm of linguistics and refers to the arrangement of words in a sentence. Similarly, an image can be considered as a visual 'sentence', with the semantic parts of the image acting as 'words'. While visual…

Computer Vision and Pattern Recognition · Computer Science 2024-02-01 Sayeed Shafayet Chowdhury , Soumyadeep Chandra , Kaushik Roy

Transformers have a remarkable ability to learn and execute tasks based on examples provided within the input itself, without explicit prior training. It has been argued that this capability, known as in-context learning (ICL), is a…

Machine Learning · Statistics 2025-10-06 Yue M. Lu , Mary I. Letey , Jacob A. Zavatone-Veth , Anindita Maiti , Cengiz Pehlevan

Disentanglement is the task of learning representations that identify and separate factors that explain the variation observed in data. Disentangled representations are useful to increase the generalizability, explainability, and fairness…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-09 Michael Kuhlmann , Adrian Meise , Fritz Seebauer , Petra Wagner , Reinhold Haeb-Umbach

We study feature learning in two-layer neural networks within the linear-width regime, where the number of hidden neurons, sample size, and input dimension scale proportionally. While recent work has analyzed feature learning via a single…

Machine Learning · Statistics 2026-05-25 Behrad Moniri , Hamed Hassani

Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations. However, existing algorithms typically require a large number of…

Machine Learning · Computer Science 2023-06-14 Tianxiang Zhao , Wenchao Yu , Suhang Wang , Lu Wang , Xiang Zhang , Yuncong Chen , Yanchi Liu , Wei Cheng , Haifeng Chen

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Machine Learning · Computer Science 2021-10-26 Jungsoo Lee , Eungyeup Kim , Juyoung Lee , Jihyeon Lee , Jaegul Choo

It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most…

Deep learning empirically achieves high performance in many applications, but its training dynamics has not been fully understood theoretically. In this paper, we explore theoretical analysis on training two-layer ReLU neural networks in a…

Machine Learning · Statistics 2021-06-30 Shunta Akiyama , Taiji Suzuki