English
Related papers

Related papers: Logarithmic-time Schedules for Scaling Language Mo…

200 papers

Is the standard weight decay in AdamW truly optimal? Although AdamW decouples weight decay from adaptive gradient scaling, a fundamental conflict remains: the Radial Tug-of-War. In deep learning, gradients tend to increase parameter norms…

Machine Learning · Computer Science 2026-02-06 Hao Chen , Jinghui Yuan , Hanmin Zhang

One very important hyperparameter for training deep neural networks is the learning rate schedule of the optimizer. The choice of learning rate schedule determines the computational cost of getting close to a minima, how close you actually…

Machine Learning · Computer Science 2021-06-01 Nikhil Iyer , V Thejas , Nipun Kwatra , Ramachandran Ramjee , Muthian Sivathanu

Large Language Models (LLMs) pruning seeks to remove unimportant weights for inference speedup with minimal accuracy impact. However, existing methods often suffer from accuracy degradation without full-model sparsity-aware fine-tuning.…

In contrast to SGD, adaptive gradient methods like Adam allow robust training of modern deep networks, especially large language models. However, the use of adaptivity not only comes at the cost of extra memory but also raises the…

Machine Learning · Computer Science 2022-07-20 Zhiyuan Li , Srinadh Bhojanapalli , Manzil Zaheer , Sashank J. Reddi , Sanjiv Kumar

Speech enhancement models should meet very low latency requirements typically smaller than 5 ms for hearing assistive devices. While various low-latency techniques have been proposed, comparing these methods in a controlled setup using DNNs…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-17 Haibin Wu , Sebastian Braun

We present a framework in which a large language model (LLM) acts as an online adaptive controller for SIMP topology optimization, replacing conventional fixed-schedule continuation with real-time, state-conditioned parameter decisions. At…

Computational Engineering, Finance, and Science · Computer Science 2026-05-18 Shaoliang Yang , Jun Wang , Yunsheng Wang

Learning the value function of a given policy from data samples is an important problem in Reinforcement Learning. TD($\lambda$) is a popular class of algorithms to solve this problem. However, the weights assigned to different $n$-step…

Machine Learning · Computer Science 2021-11-24 Rohan Deb , Meet Gandhi , Shalabh Bhatnagar

Scale has become a main ingredient in obtaining strong machine learning models. As a result, understanding a model's scaling properties is key to effectively designing both the right training setup as well as future generations of…

Machine Learning · Computer Science 2024-10-18 Alexander Hägele , Elie Bakouch , Atli Kosson , Loubna Ben Allal , Leandro Von Werra , Martin Jaggi

Low-rank adaptation (LoRA) has become the default approach to fine-tune large language models (LLMs) due to its significant reduction in trainable parameters. However, trainable parameter demand for LoRA increases with increasing model…

Computation and Language · Computer Science 2024-06-19 Seyedarmin Azizi , Souvik Kundu , Massoud Pedram

Commonly used optimization algorithms often show a trade-off between good generalization and fast training times. For instance, stochastic gradient descent (SGD) tends to have good generalization; however, adaptive gradient methods have…

Machine Learning · Computer Science 2023-06-14 Aditya Cowsik , Tankut Can , Paolo Glorioso

Large reasoning models (LRMs) achieve strong performance through extended reasoning traces, but they often exhibit overthinking behavior for low-complexity queries. Existing efforts to mitigate this issue are fundamentally limited by…

Machine Learning · Computer Science 2026-02-27 Zihang Xu , Haozhi Xie , Ziqi Miao , Wuxuan Gong , Chen Qian , Lijun Li

Loss spikes remain a persistent obstacle in large-scale language model pretraining. While previous research has attempted to identify the root cause of loss spikes by investigating individual factors, we observe that, in practice, such…

Machine Learning · Computer Science 2026-02-24 Guoxia Wang , Shuai Li , Congliang Chen , Jinle Zeng , Jiabin Yang , Dianhai Yu , Yanjun Ma , Li Shen

We investigate the role of learning rate scheduling in the large-scale pre-training of large language models, focusing on its influence on downstream performance after supervised fine-tuning (SFT). Decay-based learning rate schedulers are…

Computation and Language · Computer Science 2026-03-18 Kazuki Yano , Shun Kiyono , Sosuke Kobayashi , Sho Takase , Jun Suzuki

Compressed Deep Learning (DL) models are essential for deployment in resource-constrained environments. But their performance often lags behind their large-scale counterparts. To bridge this gap, we propose Alignment Adapter (AlAd): a…

Machine Learning · Computer Science 2026-02-17 Rohit Raj Rai , Abhishek Dhaka , Amit Awekar

The delta-bar-delta algorithm is recognized as a learning rate adaptation technique that enhances the convergence speed of the training process in optimization by dynamically scheduling the learning rate based on the difference between the…

Machine Learning · Computer Science 2023-10-18 Zhao Song , Chiwun Yang

The widely-used, weight-only quantized large language models (LLMs), which leverage low-bit integer (INT) weights and retain floating-point (FP) activations, reduce storage requirements while maintaining accuracy. However, this shifts the…

Hardware Architecture · Computer Science 2025-05-13 Chao Fang , Man Shi , Robin Geens , Arne Symons , Zhongfeng Wang , Marian Verhelst

Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning. Prior work has shown that outcome-based reinforcement learning (RL) can incidentally elicit advanced reasoning behaviors such as…

Computation and Language · Computer Science 2025-05-28 Zhiyuan Hu , Yibo Wang , Hanze Dong , Yuhui Xu , Amrita Saha , Caiming Xiong , Bryan Hooi , Junnan Li

The quality of Large Language Model (LLM) pretraining depends on multiple factors, including the compute budget and the choice of optimization algorithm. Empirical scaling laws are widely used to predict loss as model size and training data…

Machine Learning · Computer Science 2026-02-25 Alexandra Volkova , Mher Safaryan , Christoph H. Lampert , Dan Alistarh

Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensive situations. However, the relationship between parametric knowledge acquired during pretraining…

Computation and Language · Computer Science 2026-04-02 Karan Singh , Michael Yu , Varun Gangal , Zhuofu Tao , Sachin Kumar , Emmy Liu , Steven Y. Feng

Optimizers are crucial for the efficient training of Large Language Models (LLMs). While AdamW is the de facto standard, recent structure-aware optimizers like Muon have emerged, which regularize gradient updates by operating on entire…

Machine Learning · Computer Science 2025-10-07 Zehua Liu , Han Wu , Xiaojin Fu , Shuqi Liu , Xiongwei Han , Tao Zhong , Mingxuan Yuan