English
Related papers

Related papers: Learning Compositional Functions with Transformers…

200 papers

We investigate the geometric structure of learning dynamics in overparameterized transformer models through carefully controlled modular arithmetic tasks. Our primary finding is that despite operating in high-dimensional parameter spaces…

Machine Learning · Computer Science 2026-02-16 Yongzhong Xu

This paper presents a new algorithm for online linear regression whose efficiency guarantees satisfy the requirements of the KWIK (Knows What It Knows) framework. The algorithm improves on the complexity bounds of the current…

Machine Learning · Computer Science 2012-05-14 Thomas J. Walsh , Istvan Szita , Carlos Diuk , Michael L. Littman

We study \emph{learning-to-sample} -- a basic algorithmic task underlying generative modeling -- for Ising models, a standard testbed for algorithmic ideas in both theoretical computer science and machine learning. Given i.i.d. samples of…

Machine Learning · Computer Science 2026-05-26 Andrej Risteski , Thuy-Duong Vuong

Understanding the training dynamics of transformers is important to explain the impressive capabilities behind large language models. In this work, we study the dynamics of training a shallow transformer on a task of recognizing…

Machine Learning · Computer Science 2024-10-15 Hongru Yang , Bhavya Kailkhura , Zhangyang Wang , Yingbin Liang

Meta-learning algorithms adapt quickly to new tasks that are drawn from the same task distribution as the training tasks. The mechanism leading to fast adaptation is the conditioning of a downstream predictive model on the inferred…

Machine Learning · Computer Science 2021-07-23 Muhammad Waleed Gondal , Shruti Joshi , Nasim Rahaman , Stefan Bauer , Manuel Wüthrich , Bernhard Schölkopf

Collecting robotic manipulation data is expensive, making it impractical to acquire demonstrations for the combinatorially large space of tasks that arise in multi-object, multi-robot, and multi-environment settings. While recent generative…

Positional encodings enable Transformers to incorporate sequential information, yet their theoretical understanding remains limited to two properties: distance attenuation and translation invariance. Because natural language lacks purely…

Machine Learning · Computer Science 2026-02-11 Zihan Gu , Ruoyu Chen , Han Zhang , Hua Zhang , Yue Hu

Music generated by deep learning methods often suffers from a lack of coherence and long-term organization. Yet, multi-scale hierarchical structure is a distinctive feature of music signals. To leverage this information, we propose a…

Sound · Computer Science 2024-02-29 Manvi Agarwal , Changhong Wang , Gaël Richard

Transductive tasks on graphs differ fundamentally from typical supervised machine learning tasks, as the independent and identically distributed (i.i.d.) assumption does not hold among samples. Instead, all train/test/validation samples are…

Machine Learning · Computer Science 2024-11-21 Hamed Shirzad , Honghao Lin , Ameya Velingker , Balaji Venkatachalam , David Woodruff , Danica Sutherland

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

While Transformer architectures have show remarkable success, they are bound to the computation of all pairwise interactions of input element and thus suffer from limited scalability. Recent work has been successful by avoiding the…

Machine Learning · Computer Science 2021-02-16 Max Horn , Kumar Shridhar , Elrich Groenewald , Philipp F. M. Baumann

Transformers are widely used across data modalities, and yet the principles distilled from text models often transfer imperfectly to models trained to other modalities. In this paper, we analyze Transformers through the lens of rank…

Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the…

Computation and Language · Computer Science 2020-01-16 Jean Maillard , Stephen Clark

Large language models (LLMs) are primarily designed to understand unstructured text. When directly applied to structured formats such as tabular data, they may struggle to discern inherent relationships and overlook critical patterns. While…

Machine Learning · Computer Science 2024-10-11 Natraj Raman , Sumitra Ganesh , Manuela Veloso

It is well known that most of the conventional video question answering (VideoQA) datasets consist of easy questions requiring simple reasoning processes. However, long videos inevitably contain complex and compositional semantic structures…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Jihyeon Lee , Wooyoung Kang , Eun-Sol Kim

We present *-CFQ ("star-CFQ"): a suite of large-scale datasets of varying scope based on the CFQ semantic parsing benchmark, designed for principled investigation of the scalability of machine learning systems in a realistic compositional…

Machine Learning · Computer Science 2020-12-16 Dmitry Tsarkov , Tibor Tihon , Nathan Scales , Nikola Momchev , Danila Sinopalnikov , Nathanael Schärli

The composition of elementary behaviors to solve challenging transfer learning problems is one of the key elements in building intelligent machines. To date, there has been plenty of work on learning task-specific policies or skills but…

Machine Learning · Computer Science 2020-01-01 Ahmed H. Qureshi , Jacob J. Johnson , Yuzhe Qin , Taylor Henderson , Byron Boots , Michael C. Yip

Previous multi-task dense prediction studies developed complex pipelines such as multi-modal distillations in multiple stages or searching for task relational contexts for each task. The core insight beyond these methods is to maximize the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Yangyang Xu , Xiangtai Li , Haobo Yuan , Yibo Yang , Lefei Zhang

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…

Machine Learning · Computer Science 2020-02-19 Nikita Kitaev , Łukasz Kaiser , Anselm Levskaya

Feed-forward layers constitute two-thirds of a transformer model's parameters, yet their role in the network remains under-explored. We show that feed-forward layers in transformer-based language models operate as key-value memories, where…

Computation and Language · Computer Science 2021-09-07 Mor Geva , Roei Schuster , Jonathan Berant , Omer Levy
‹ Prev 1 8 9 10 Next ›