all AI news
Efficient Global Optimization of Two-layer ReLU Networks: Quadratic-time Algorithms and Adversarial Training. (arXiv:2201.01965v1 [cs.LG])
Jan. 7, 2022, 2:10 a.m. | Yatong Bai, Tanmay Gautam, Somayeh Sojoudi
cs.LG updates on arXiv.org arxiv.org
The non-convexity of the artificial neural network (ANN) training landscape
brings inherent optimization difficulties. While the traditional
back-propagation stochastic gradient descent (SGD) algorithm and its variants
are effective in certain cases, they can become stuck at spurious local minima
and are sensitive to initializations and hyperparameters. Recent work has shown
that the training of an ANN with ReLU activations can be reformulated as a
convex program, bringing hope to globally optimizing interpretable ANNs.
However, naively solving the convex training formulation …
More from arxiv.org / cs.LG updates on arXiv.org
Generalized Schr\"odinger Bridge Matching
1 day, 8 hours ago |
arxiv.org
Tight bounds on Pauli channel learning without entanglement
1 day, 8 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Lead Software Engineer - Artificial Intelligence, LLM
@ OpenText | Hyderabad, TG, IN
Lead Software Engineer- Python Data Engineer
@ JPMorgan Chase & Co. | GLASGOW, LANARKSHIRE, United Kingdom
Data Analyst (m/w/d)
@ Collaboration Betters The World | Berlin, Germany
Data Engineer, Quality Assurance
@ Informa Group Plc. | Boulder, CO, United States
Director, Data Science - Marketing
@ Dropbox | Remote - Canada