English
Related papers

Related papers: Q-Ensemble for Offline RL: Don't Scale the Ensembl…

200 papers

Offline reinforcement learning proposes to learn policies from large collected datasets without interacting with the physical environment. These algorithms have made it possible to learn useful skills from data that can then be deployed in…

Machine Learning · Computer Science 2021-07-06 Samarth Sinha , Ajay Mandlekar , Animesh Garg

Scheduling the batch size to increase is an effective strategy to control gradient noise when training deep neural networks. Current approaches implement scheduling heuristics that neglect structure within the optimization procedure,…

Machine Learning · Computer Science 2022-05-18 Calum Robert MacLellan , Feng Dong

The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research…

Machine Learning · Computer Science 2021-02-12 Mengjiao Yang , Ofir Nachum

Deep neural networks are commonly trained using stochastic non-convex optimization procedures, which are driven by gradient information estimated on fractions (batches) of the dataset. While it is commonly accepted that batch size is an…

Machine Learning · Computer Science 2016-04-26 Ilya Loshchilov , Frank Hutter

Deep learning systems are optimized for clusters with homogeneous resources. However, heterogeneity is prevalent in computing infrastructure across edge, cloud and HPC. When training neural networks using stochastic gradient descent…

Machine Learning · Computer Science 2025-03-25 Sahil Tyagi , Prateek Sharma

Ensemble learning is a popular technique to improve the accuracy of machine learning models. It traditionally hinges on the rationale that aggregating multiple weak models can lead to better models with lower variance and hence higher…

Optimization and Control · Mathematics 2026-01-06 Huajie Qian , Donghao Ying , Henry Lam , Wotao Yin

Learning rate schedule has a major impact on the performance of deep learning models. Still, the choice of a schedule is often heuristical. We aim to develop a precise understanding of the effects of different learning rate schedules and…

Machine Learning · Computer Science 2020-02-25 Guillaume Leclerc , Aleksander Madry

Active learning parallelization is widely used, but typically relies on fixing the batch size throughout experimentation. This fixed approach is inefficient because of a dynamic trade-off between cost and speed -- larger batches are more…

Machine Learning · Computer Science 2024-10-15 Masaki Adachi , Satoshi Hayakawa , Martin Jørgensen , Xingchen Wan , Vu Nguyen , Harald Oberhauser , Michael A. Osborne

Increasing the batch size during training -- a ''batch ramp'' -- is a promising strategy to accelerate large language model pretraining. While for SGD, doubling the batch size can be equivalent to halving the learning rate, the optimal…

Machine Learning · Computer Science 2025-10-17 Alexandru Meterez , Depen Morwani , Jingfeng Wu , Costin-Andrei Oncescu , Cengiz Pehlevan , Sham Kakade

Dramatic increases in the capabilities of neural network models in recent years are driven by scaling model size, training data, and corresponding computational resources. To develop the exceedingly large networks required in modern…

Machine Learning · Computer Science 2025-04-15 Jared Fernandez , Luca Wehrstedt , Leonid Shamis , Mostafa Elhoushi , Kalyan Saladi , Yonatan Bisk , Emma Strubell , Jacob Kahn

Due to the dominant position of deep learning (mostly deep neural networks) in various artificial intelligence applications, recently, ensemble learning based on deep neural networks (ensemble deep learning) has shown significant…

Machine Learning · Computer Science 2022-11-07 Yongquan Yang , Haijun Lv , Ning Chen

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

Machine Learning · Computer Science 2025-10-07 Lianghuan Huang , Sagnik Anupam , Insup Lee , Shuo Li , Osbert Bastani

In this brief, we improve the Broad Learning System (BLS) [7] by reducing the computational complexity of the incremental learning for added inputs. We utilize the inverse of a sum of matrices in [8] to improve a step in the pseudoinverse…

Machine Learning · Computer Science 2022-11-21 Hufei Zhu , Zhulin Liu , C. L. Philip Chen , Yanyang Liang

Deep learning has become very popular for tasks such as predictive modeling and pattern recognition in handling big data. Deep learning is a powerful machine learning method that extracts lower level features and feeds them forward for the…

Machine Learning · Computer Science 2018-03-07 Steven Young , Tamer Abdou , Ayse Bener

The most straightforward method to accelerate Stochastic Gradient Descent (SGD) computation is to distribute the randomly selected batch of inputs over multiple processors. To keep the distributed processors fully utilized requires…

Machine Learning · Computer Science 2020-01-06 Zhewei Yao , Amir Gholami , Daiyaan Arfeen , Richard Liaw , Joseph Gonzalez , Kurt Keutzer , Michael Mahoney

Reinforcement learning (RL) with limited samples is common in real-world applications. However, offline RL performance under this constraint is often suboptimal. We consider an alternative approach to dealing with limited samples by…

Machine Learning · Computer Science 2025-11-14 Outongyi Lv , Yewei Yuan , Nana Liu

Scaling distributed training of Large Language Models (LLMs) requires not only algorithmic advances but also efficient utilization of heterogeneous hardware resources. While existing methods such as DiLoCo have demonstrated promising…

The success of deep learning in the computer vision and natural language processing communities can be attributed to training of very deep neural networks with millions or billions of parameters which can then be trained with massive…

Machine Learning · Computer Science 2021-02-17 Kei Ota , Devesh K. Jha , Asako Kanezaki

The motivation of this work is to improve the performance of standard stacking approaches or ensembles, which are composed of simple, heterogeneous base models, through the integration of the generation and selection stages for regression…

Machine Learning · Statistics 2014-03-31 Roberto Aldave , Jean-Pierre Dussault

Recently, sparse training methods have started to be established as a de facto approach for training and inference efficiency in artificial neural networks. Yet, this efficiency is just in theory. In practice, everyone uses a binary mask to…

Machine Learning · Computer Science 2022-07-13 Selima Curci , Decebal Constantin Mocanu , Mykola Pechenizkiyi