English
Related papers

Related papers: Optimizer-Induced Low-Dimensional Drift and Transv…

200 papers

How does the choice of optimization algorithm shape a model's ability to learn features? To address this question for steepest descent methods --including sign descent, which is closely related to Adam --we introduce steepest mirror flows…

Machine Learning · Computer Science 2026-03-03 Tom Jacobs , Chao Zhou , Rebekka Burkholz

We address the challenge of representation learning from a continuous stream of video as input, in a self-supervised manner. This differs from the standard approaches to video learning where videos are chopped and shuffled during training…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Tengda Han , Dilara Gokay , Joseph Heyward , Chuhan Zhang , Daniel Zoran , Viorica Pătrăucean , João Carreira , Dima Damen , Andrew Zisserman

Despite their widespread use, training deep Transformers can be unstable. Layer normalization, a standard component, improves training stability, but its placement has often been ad-hoc. In this paper, we conduct a principled study on the…

Machine Learning · Computer Science 2025-10-14 Kelvin Kan , Xingjian Li , Benjamin J. Zhang , Tuhin Sahai , Stanley Osher , Krishna Kumar , Markos A. Katsoulakis

Long-horizon LM agents learn from multi-turn interaction, where a single early mistake can alter the subsequent state distribution and derail the whole trajectory. Existing recipes fall short in complementary ways: supervised fine-tuning…

Machine Learning · Computer Science 2026-05-14 Changhao Li , Rushi Qiang , Jiawei Huang , Chenxiao Gao , Chao Zhang , Niao He , Bo Dai

Solving inverse problems, such as parameter estimation and optimal control, is a vital part of science. Many experiments repeatedly collect data and rely on machine learning algorithms to quickly infer solutions to the associated inverse…

Machine Learning · Computer Science 2022-10-14 Philipp Holl , Vladlen Koltun , Nils Thuerey

We propose a novel framework for learning stabilizable nonlinear dynamical systems for continuous control tasks in robotics. The key contribution is a control-theoretic regularizer for dynamics fitting rooted in the notion of…

Optimization and Control · Mathematics 2019-08-01 Sumeet Singh , Spencer M. Richards , Vikas Sindhwani , Jean-Jacques E. Slotine , Marco Pavone

Trajectory forecasting for autonomous driving must deliver accurate, calibrated multi-modal futures under tight compute and latency constraints. We propose a compact hybrid quantum architecture that aligns quantum inductive bias with…

Machine Learning · Computer Science 2025-11-25 Navneet Singh , Shiva Raj Pokhrel

Adaptive gradient methods, e.g. \textsc{Adam}, have achieved tremendous success in machine learning. Scaling the learning rate element-wisely by a certain form of second moment estimate of gradients, such methods are able to attain rapid…

Machine Learning · Computer Science 2022-02-10 Yizhou Wang , Yue Kang , Can Qin , Huan Wang , Yi Xu , Yulun Zhang , Yun Fu

In modern deep learning, the models are learned by applying gradient updates using an optimizer, which transforms the updates based on various statistics. Optimizers are often hand-designed and tuning their hyperparameters is a big part of…

Machine Learning · Computer Science 2024-10-08 Gus Kristiansen , Mark Sandler , Andrey Zhmoginov , Nolan Miller , Anirudh Goyal , Jihwan Lee , Max Vladymyrov

Some autoregressive models exhibit in-context learning capabilities: being able to learn as an input sequence is processed, without undergoing any parameter changes, and without being explicitly trained to do so. The origins of this…

Transformer models have recently garnered significant attention in image restoration due to their ability to capture long-range pixel dependencies. However, long-range attention often results in computational overhead without practical…

Computer Vision and Pattern Recognition · Computer Science 2025-04-24 Qifan Li , Tianyi Liang , Xingtao Wang , Xiaopeng Fan

Two meta-evolutionary optimization strategies described in this paper accelerate the convergence of evolutionary programming algorithms while still retaining much of their ability to deal with multi-modal problems. The strategies, called…

Neural and Evolutionary Computing · Computer Science 2009-03-26 Ted Dunning

We introduce directional routing, a lightweight mechanism that gives each transformer attention head learned suppression directions controlled by a shared router, at 3.9% parameter cost. We train a 433M-parameter model alongside an…

Machine Learning · Computer Science 2026-03-17 Kevin Taylor

Rapid and accurate building damage assessment in the immediate aftermath of tornadoes is critical for coordinating life-saving search and rescue operations, optimizing emergency resource allocation, and accelerating community recovery.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Robinson Umeike , Thang Dao , Shane Crawford , John van de Lindt , Blythe Johnston , Wanting , Wang , Trung Do , Ajibola Mofikoya , Sarbesh Banjara , Cuong Pham

We study the fundamental optimization principles of self-attention, the defining mechanism of transformers, by analyzing the implicit bias of gradient-based optimizers in training a self-attention layer with a linear decoder in binary…

Machine Learning · Computer Science 2025-04-01 Bhavya Vasudeva , Puneesh Deora , Christos Thrampoulidis

Autonomous driving (AD) technology, leveraging artificial intelligence, strives for vehicle automation. End-toend strategies, emerging to simplify traditional driving systems by integrating perception, decision-making, and control, offer…

Robotics · Computer Science 2024-03-19 Dong Hu , Chao Huang , Jingda Wu , Hongbo Gao

Classification and localization of driving actions over time is important for advanced driver-assistance systems and naturalistic driving studies. Temporal localization is challenging because it requires robustness, reliability, and…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Erkut Akdag , Zeqi Zhu , Egor Bondarev , Peter H. N. De With

Diffusion models currently dominate the field of data-driven image synthesis with their unparalleled scaling to large datasets. In this paper, we identify and rectify several causes for uneven and ineffective training in the popular ADM…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Tero Karras , Miika Aittala , Jaakko Lehtinen , Janne Hellsten , Timo Aila , Samuli Laine

Adaptive gradient optimizers like Adam(W) are the default training algorithms for many deep learning architectures, such as transformers. Their diagonal preconditioner is based on the gradient outer product which is incorporated into the…

Machine Learning · Computer Science 2024-10-08 Wu Lin , Felix Dangel , Runa Eschenhagen , Juhan Bae , Richard E. Turner , Alireza Makhzani

We show that replacing the rolling SVD of AdamW updates with a rolling SVD of loss gradients changes the diagnostic by 1-2 orders of magnitude. Performing SVD on the loss gradient instead of the AdamW update increases the measured…

Machine Learning · Computer Science 2026-04-29 Yongzhong Xu
‹ Prev 1 3 4 5 6 7 10 Next ›