English
Related papers

Related papers: Capacity Matters: a Proof-of-Concept for Transform…

200 papers

When do diffusion models reproduce their training data, and when are they able to generate samples beyond it? A practically relevant theoretical understanding of this interplay between memorization and generalization may significantly…

Machine Learning · Computer Science 2025-08-26 Sam Buchanan , Druv Pai , Yi Ma , Valentin De Bortoli

We study Transformers through the perspective of optimal control theory, using tools from continuous-time formulations to derive actionable insights into training and architecture design. This framework improves the performance of existing…

Machine Learning · Computer Science 2025-10-27 Kelvin Kan , Xingjian Li , Benjamin J. Zhang , Tuhin Sahai , Stanley Osher , Markos A. Katsoulakis

Despite the empirical advances of deep learning across a variety of learning tasks, our theoretical understanding of its success is still very restricted. One of the key challenges is the overparametrized nature of modern models, enabling…

Machine Learning · Computer Science 2023-02-24 Sotiris Anagnostidis , Gregor Bachmann , Lorenzo Noci , Thomas Hofmann

Memory constraint of always-on devices is one of the major concerns when deploying speech processing models on these devices. While larger models trained with sufficiently large amount of data generally perform better, making them fit in…

Computation and Language · Computer Science 2024-01-09 Yiming Wang , Jinyu Li

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…

Machine Learning · Computer Science 2019-03-21 Hung Le , Truyen Tran , Svetha Venkatesh

Recent works have shown that diffusion models are able to memorize training images and emit them at generation time. However, the metrics used to evaluate memorization and its mitigation techniques suffer from dataset-dependent biases and…

Machine Learning · Computer Science 2025-03-04 Nicky Kriplani , Minh Pham , Gowthami Somepalli , Chinmay Hegde , Niv Cohen

Neural networks encounter the challenge of Catastrophic Forgetting (CF) in continual learning, where new task learning interferes with previously learned knowledge. Existing data fine-tuning and regularization methods necessitate task…

Machine Learning · Computer Science 2024-05-17 Yuwei Sun , Ippei Fujisawa , Arthur Juliani , Jun Sakuma , Ryota Kanai

Building models of natural language processing (NLP) is challenging in low-resource scenarios where only limited data are available. Optimization-based meta-learning algorithms achieve promising results in low-resource scenarios by adapting…

Computation and Language · Computer Science 2022-07-15 Yingxiu Zhao , Zhiliang Tian , Huaxiu Yao , Yinhe Zheng , Dongkyu Lee , Yiping Song , Jian Sun , Nevin L. Zhang

Despite the remarkable success of transformer architectures in natural language processing, their scalability limitations remain poorly understood through systematic empirical analysis. This paper presents the first comprehensive…

Machine Learning · Computer Science 2026-05-18 Mahdi Naser Moghadasi , Faezeh Ghaderi

Much of recent Deep Reinforcement Learning success is owed to the neural architecture's potential to learn and use effective internal representations of the world. While many current algorithms access a simulator to train with a large…

Artificial Intelligence · Computer Science 2022-02-03 Amir Ardalan Kalantari , Mohammad Amini , Sarath Chandar , Doina Precup

Due to their black-box and data-hungry nature, deep learning techniques are not yet widely adopted for real-world applications in critical domains, like healthcare and justice. This paper presents Memory Wrap, a plug-and-play extension to…

Machine Learning · Computer Science 2023-10-30 Biagio La Rosa , Roberto Capobianco , Daniele Nardi

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Laziz U. Abdullaev , Maksim Tkachenko , Tan M. Nguyen

This work focuses on the training dynamics of one associative memory module storing outer products of token embeddings. We reduce this problem to the study of a system of particles, which interact according to properties of the data…

Machine Learning · Computer Science 2024-03-01 Vivien Cabannes , Berfin Simsek , Alberto Bietti

Transformer-based architectures represent the state of the art in sequence modeling tasks like machine translation and language understanding. Their applicability to multi-modal contexts like image captioning, however, is still largely…

Computer Vision and Pattern Recognition · Computer Science 2020-03-24 Marcella Cornia , Matteo Stefanini , Lorenzo Baraldi , Rita Cucchiara

Individual neurons in neural networks often represent a mixture of unrelated features. This phenomenon, called polysemanticity, can make interpreting neural networks more difficult and so we aim to understand its causes. We propose doing so…

Neural and Evolutionary Computing · Computer Science 2025-03-26 Adam Scherlis , Kshitij Sachan , Adam S. Jermyn , Joe Benton , Buck Shlegeris

The maximum element of the vector output by the Softmax function approaches zero as the input vector size increases. Transformer-based language models rely on Softmax to compute attention scores, causing the attention distribution to…

Computation and Language · Computer Science 2025-02-03 Ken M. Nakanishi

Recent work has shown that transformer-based language models learn rich geometric structure in their embedding spaces. In this work, we investigate whether sentence embeddings exhibit structured geometric organization aligned with…

Computation and Language · Computer Science 2026-04-07 Sophie Zhao

Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication overhead. We introduce STEM (Scaling Transformers with…

In this work, we propose a new class of learnable optimizers, called \textit{Mnemosyne}. It is based on the novel spatio-temporal low-rank implicit attention Transformers that can learn to train entire neural network architectures,…

Machine Learning · Computer Science 2023-06-21 Deepali Jain , Krzysztof Marcin Choromanski , Avinava Dubey , Sumeet Singh , Vikas Sindhwani , Tingnan Zhang , Jie Tan

Large Language Models (LLMs) are prevalent in modern applications but often memorize training data, leading to privacy breaches and copyright issues. Existing research has mainly focused on posthoc analyses, such as extracting memorized…

Machine Learning · Computer Science 2025-01-10 Tarun Ram Menta , Susmit Agrawal , Chirag Agarwal
‹ Prev 1 8 9 10 Next ›