English
Related papers

Related papers: Winner-Take-All Column Row Sampling for Memory Eff…

200 papers

Adaptive gradient-based optimizers such as Adagrad and Adam are crucial for achieving state-of-the-art performance in machine translation and language modeling. However, these methods maintain second-order statistics for each parameter,…

Machine Learning · Computer Science 2019-09-13 Rohan Anil , Vineet Gupta , Tomer Koren , Yoram Singer

To improve the efficiency and sustainability of learning deep models, we propose CREST, the first scalable framework with rigorous theoretical guarantees to identify the most valuable examples for training non-convex models, particularly…

Machine Learning · Computer Science 2023-06-05 Yu Yang , Hao Kang , Baharan Mirzasoleiman

Self-supervised learning, a.k.a., pretraining, is important in natural language processing. Most of the pretraining methods first randomly mask some positions in a sentence and then train a model to recover the tokens at the masked…

Computation and Language · Computer Science 2020-08-18 Liang Chen

Recurrent neural networks (RNNs) have shown promising performance for language modeling. However, traditional training of RNNs using back-propagation through time often suffers from overfitting. One reason for this is that stochastic…

Computation and Language · Computer Science 2017-04-25 Zhe Gan , Chunyuan Li , Changyou Chen , Yunchen Pu , Qinliang Su , Lawrence Carin

Stochastic neurons can be useful for a number of reasons in deep learning models, but in many cases they pose a challenging problem: how to estimate the gradient of a loss function with respect to the input of such stochastic neurons, i.e.,…

Machine Learning · Computer Science 2013-05-15 Yoshua Bengio

The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated attention variants that…

Artificial Intelligence · Computer Science 2026-01-23 Alfred Shen , Aaron Shen

Neural network training relies on gradient computation through backpropagation, yet memory requirements for storing layer activations present significant scalability challenges. We present the first adaptation of control-theoretic matrix…

Machine Learning · Computer Science 2025-10-02 Harbir Antil , Deepanshu Verma

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with…

Computation and Language · Computer Science 2025-01-16 Yuxuan Hu , Jing Zhang , Xiaodong Chen , Zhe Zhao , Cuiping Li , Hong Chen

The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…

Hardware neural networks that implement synaptic weights with embedded non-volatile memory, such as spin torque memory (ST-MRAM), are a major lead for low energy artificial intelligence. In this work, we propose an approximate storage…

Emerging Technologies · Computer Science 2018-10-26 Nicolas Locatelli , Adrien F. Vincent , Damien Querlioz

Column Type Annotation (CTA) is a fundamental step towards enabling schema alignment and semantic understanding of tabular data. Existing encoder-only language models achieve high accuracy when fine-tuned on labeled columns, but their…

Databases · Computer Science 2025-12-30 Hanze Meng , Jianhao Cao , Rachel Pottinger

Large language models (LLMs) are increasingly being deployed in cost and latency-sensitive settings. While chain-of-thought improves reasoning, it can waste tokens on simple requests. We study selective thinking for tool-using LLMs and…

In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time. State of the art models such as LSTM and Transformer are trained by backpropagation of…

Machine Learning · Computer Science 2019-12-04 Jeremy Gordon , David Rawlinson , Subutai Ahmad

Kernel matrices (e.g. Gram or similarity matrices) are essential for many state-of-the-art approaches to classification, clustering, and dimensionality reduction. For large datasets, the cost of forming and factoring such kernel matrices…

Machine Learning · Statistics 2015-05-21 Raajen Patel , Thomas A. Goldstein , Eva L. Dyer , Azalia Mirhoseini , Richard G. Baraniuk

The neural transducer is an end-to-end model for automatic speech recognition (ASR). While the model is well-suited for streaming ASR, the training process remains challenging. During training, the memory requirements may quickly exceed the…

Computation and Language · Computer Science 2023-03-14 Stefan Braun , Erik McDermott , Roger Hsiao

The recent paradigm shift to large-scale foundation models has brought about a new era for deep learning that, while has found great success in practice, has also been plagued by prohibitively expensive costs in terms of high memory…

Machine Learning · Computer Science 2025-05-21 Stephen Zhang , Vardan Papyan

Fully finetuning foundation language models (LMs) with billions of parameters is often impractical due to high computational costs, memory requirements, and the risk of overfitting. Although methods like low-rank adapters help address these…

Machine Learning · Computer Science 2026-02-11 Jonathan Svirsky , Yehonathan Refael , Ofir Lindenbaum

Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, and forms the bedrock of modern machine learning and statistics. In this work, we seek to balance the fact that attenuating step-size is…

Signal Processing · Electrical Eng. & Systems 2020-07-10 Zhan Gao , Alec Koppel , Alejandro Ribeiro

Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters associated with the…

Computation and Language · Computer Science 2018-02-26 Chao Zhang , Philip Woodland

Neural language models (LMs) have been proved to significantly outperform classical n-gram LMs for language modeling due to their superior abilities to model long-range dependencies in text and handle data sparsity problems. And recently,…

Computation and Language · Computer Science 2019-10-28 Hongzhao Huang , Fuchun Peng