Zobrazeno 1 - 10
of 2 037
pro vyhledávání: '"Thérien A"'
Autor:
Thérien, Benjamin, Joseph, Charles-Étienne, Knyazev, Boris, Oyallon, Edouard, Rish, Irina, Belilovsky, Eugene
Learned optimizers (LOs) can significantly reduce the wall-clock training time of neural networks, substantially reducing training costs. However, they often suffer from poor meta-generalization, especially when training networks larger than those se
Externí odkaz:
http://arxiv.org/abs/2406.00153
Autor:
Ibrahim, Adam, Thérien, Benjamin, Gupta, Kshitij, Richter, Mats L., Anthony, Quentin, Lesort, Timothée, Belilovsky, Eugene, Rish, Irina
Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes available. A much more efficient solution is to continually pre-train these models, saving significant compute co
Externí odkaz:
http://arxiv.org/abs/2403.08763
Autor:
Joseph, Charles-Étienne, Thérien, Benjamin, Moudgil, Abhinav, Knyazev, Boris, Belilovsky, Eugene
Communication-efficient variants of SGD, specifically local SGD, have received a great deal of interest in recent years. These approaches compute multiple gradient steps locally, that is on each worker, before averaging model parameters, helping reli
Externí odkaz:
http://arxiv.org/abs/2312.02204
Autor:
Gupta, Kshitij, Thérien, Benjamin, Ibrahim, Adam, Richter, Mats L., Anthony, Quentin, Belilovsky, Eugene, Rish, Irina, Lesort, Timothée
Large language models (LLMs) are routinely pre-trained on billions of tokens, only to restart the process over again once new data becomes available. A much cheaper and more efficient solution would be to enable the continual pre-training of these mo
Externí odkaz:
http://arxiv.org/abs/2308.04014
Object re-identification (ReID) from images plays a critical role in application domains of image retrieval (surveillance, retail analytics, etc.) and multi-object tracking (autonomous driving, robotics, etc.). However, systems that additionally or e
Externí odkaz:
http://arxiv.org/abs/2305.10210
In adversarial machine learning, the popular $\ell_\infty$ threat model has been the focus of much previous work. While this mathematical definition of imperceptibility successfully captures an infinite set of additive image transformations that a mo
Externí odkaz:
http://arxiv.org/abs/2210.02577
Imagine experiencing a crash as the passenger of an autonomous vehicle. Wouldn't you want to know why it happened? Current end-to-end optimizable deep neural networks (DNNs) in 3D detection, multi-object tracking, and motion forecasting provide littl
Externí odkaz:
http://arxiv.org/abs/2210.01266
Autor:
Huang, Chengjie, Nguyen, Van Duong, Abdelzad, Vahdat, Mannes, Christopher Gus, Rowe, Luke, Therien, Benjamin, Salay, Rick, Czarnecki, Krzysztof
3D object detection is an essential part of automated driving, and deep neural networks (DNNs) have achieved state-of-the-art performance for this task. However, deep models are notorious for assigning high confidence scores to out-of-distribution (O
Externí odkaz:
http://arxiv.org/abs/2209.14435
Autor:
Roy, Nicholas, Posner, Ingmar, Barfoot, Tim, Beaudoin, Philippe, Bengio, Yoshua, Bohg, Jeannette, Brock, Oliver, Depatie, Isabelle, Fox, Dieter, Koditschek, Dan, Lozano-Perez, Tomas, Mansinghka, Vikash, Pal, Christopher, Richards, Blake, Sadigh, Dorsa, Schaal, Stefan, Sukhatme, Gaurav, Therien, Denis, Toussaint, Marc, Van de Panne, Michiel
Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains. Consequently, the notion of applying learning methods to a particular problem set has become an established and valuable
Externí odkaz:
http://arxiv.org/abs/2110.15245
Publikováno v:
In Surgical Oncology October 2024 56