English
Related papers

Related papers: Sparsifying Transformer Models with Trainable Repr…

200 papers

Active learning has the potential to be especially useful for messy, uncurated pools where datapoints vary in relevance to the target task. However, state-of-the-art approaches to this problem currently rely on using fixed, unsupervised…

Machine Learning · Computer Science 2026-02-16 Kianoosh Ashouritaklimi , Tom Rainforth

Data is said to follow the transform (or analysis) sparsity model if it becomes sparse when acted on by a linear operator called a sparsifying transform. Several algorithms have been designed to learn such a transform directly from data,…

Machine Learning · Statistics 2019-01-30 Luke Pfister , Yoram Bresler

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

Computation and Language · Computer Science 2024-10-01 Zi Yang , Samridhi Choudhary , Siegfried Kunzmann , Zheng Zhang

A persistent paradox in time-series forecasting is that structurally simple MLP and linear models often outperform high-capacity Transformers. We argue that this gap arises from a mismatch in the sequence-modeling primitive: while many…

Machine Learning · Computer Science 2026-05-13 Jevon Twitty , Vinh Pham , Nitiwith Rotchanarak , Viresh Pati , Yubin Kim , Shihao Yang , Jiecheng Lu

We investigate the use of sparse coding and dictionary learning in the context of multitask and transfer learning. The central assumption of our learning method is that the tasks parameters are well approximated by sparse linear…

Machine Learning · Computer Science 2014-06-17 Andreas Maurer , Massimiliano Pontil , Bernardino Romera-Paredes

Accommodating long sequences efficiently in autoregressive Transformers, especially within an extended context window, poses significant challenges due to the quadratic computational complexity and substantial KV memory requirements…

Computation and Language · Computer Science 2024-06-25 Chao Lou , Zixia Jia , Zilong Zheng , Kewei Tu

During typical gradient-based training of deep neural networks, all of the model's parameters are updated at each iteration. Recent work has shown that it is possible to update only a small subset of the model's parameters during training,…

Machine Learning · Computer Science 2021-11-19 Yi-Lin Sung , Varun Nair , Colin Raffel

Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t.…

Machine Learning · Computer Science 2023-06-05 Matteo Pagliardini , Daniele Paliotta , Martin Jaggi , François Fleuret

Recent work in Deep Learning has re-imagined the representation of data as functions mapping from a coordinate space to an underlying continuous signal. When such functions are approximated by neural networks this introduces a compelling…

Machine Learning · Statistics 2022-08-09 Jonathan Richard Schwarz , Yee Whye Teh

Large language models have steadily increased in size to achieve improved performance; however, this growth has also led to greater inference time and computational demands. Consequently, there is rising interest in model size reduction…

This document contains an educational introduction to the problem of sparsifying parametric models with L0 regularization. We utilize this approach together with dictionary learning to learn sparse polynomial policies for deep reinforcement…

Machine Learning · Computer Science 2024-09-06 Nicolò Botteghi , Urban Fasel

The state of the art on many NLP tasks is currently achieved by large pre-trained language models, which require a considerable amount of computation. We explore a setting where many different predictions are made on a single piece of text.…

Computation and Language · Computer Science 2020-04-30 Jingfei Du , Myle Ott , Haoran Li , Xing Zhou , Veselin Stoyanov

With the advent of general-purpose speech representations from large-scale self-supervised models, applying a single model to multiple downstream tasks is becoming a de-facto approach. However, the pooling problem remains; the length of…

Machine Learning · Computer Science 2023-04-11 Jeongkyun Park , Kwanghee Choi , Hyunjun Heo , Hyung-Min Park

Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across high-dimensional…

Machine Learning · Computer Science 2022-12-13 Yuxuan Li , James L. McClelland

Real-world processes often contain intermediate state that can be modeled as an extremely sparse activation tensor. In this work, we analyze the identifiability of such sparse and local latent intermediate variables, which we call motifs.…

Machine Learning · Computer Science 2026-03-04 Kavi Gupta , Osbert Bastani , Armando Solar-Lezama

Transformer training is notoriously difficult, requiring a careful design of optimizers and use of various heuristics. We make progress towards understanding the subtleties of training Transformers by carefully studying a simple yet…

Machine Learning · Computer Science 2024-03-14 Kwangjun Ahn , Xiang Cheng , Minhak Song , Chulhee Yun , Ali Jadbabaie , Suvrit Sra

Transformers have impressive generalization capabilities on tasks with a fixed context length. However, they fail to generalize to sequences of arbitrary length, even for seemingly simple tasks such as duplicating a string. Moreover, simply…

Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any…

Machine Learning · Computer Science 2023-05-22 Yaniv Leviathan , Matan Kalman , Yossi Matias

The concept of sparsity has been extensively applied for regularization in image reconstruction. Typically, sparsifying transforms are either pre-trained on ground-truth images or adaptively trained during the reconstruction. Thereby,…

Image and Video Processing · Electrical Eng. & Systems 2022-03-07 Andreas Kofler , Christian Wald , Tobias Schaeffter , Markus Haltmeier , Christoph Kolbitsch

A rich representation is key to general robotic manipulation, but existing approaches to representation learning require large amounts of multimodal demonstrations. In this work we propose PLEX, a transformer-based architecture that learns…

‹ Prev 1 4 5 6 7 8 10 Next ›