Følg
Ravid Shwartz-Ziv
Tittel
Sitert av
Sitert av
År
Opening the black box of deep neural networks via information
R Shwartz-Ziv, N Tishby
Entropy, 21(219), 3390, 2019
18002019
Tabular Data: Deep Learning is Not All You Need
R Shwartz-Ziv, A Armon
Information Fusion 81, 84-90, 2022
15962022
Information Flow in Deep Neural Networks
R Shwartz Ziv
arXiv preprint arXiv:2202.06749, 2022
193*2022
To Compress or Not to Compress--Self-Supervised Learning and Information Theory: A Review
R Shwartz-Ziv, Y LeCun
arXiv preprint arXiv:2304.09355, 2023
129*2023
LiveBench: A Challenging, Contamination-Free LLM Benchmark
C White, S Dooley, M Roberts, A Pal, B Feuer, S Jain, R Shwartz-Ziv, ...
80*2024
Information in Infinite Ensembles of Infinitely-Wide Neural Networks
R Shwartz-Ziv, AA Alemi
Proceedings of the Symposium on Advances in Approximate Bayesian Inference, 2019
60*2019
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
A Chen, R Shwartz-Ziv, K Cho, ML Leavitt, N Saphra
arXiv preprint arXiv:2309.07311, 2023
582023
Representation compression and generalization in deep neural networks
R Shwartz-Ziv, A Painsky, N Tishby
https://openreview.net/pdf?id=SkeL6sCqK7, 2019
51*2019
The dual information bottleneck
Z Piran, R Shwartz-Ziv, N Tishby
https://arxiv.org/abs/2006.04641, 2020
49*2020
What Do We Maximize in Self-Supervised Learning?
R Shwartz-Ziv, R Balestriero, Y LeCun
ICML 2022: Pre-training: Perspectives, Pitfalls, and Paths Forward workshop, 2022
44*2022
Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
R Shwartz-Ziv, M Goldblum, H Souri, S Kapoor, C Zhu, Y LeCun, ...
NeurIPS 2022, 2022
432022
How much data are augmentations worth? an investigation into scaling laws, invariance, and implicit regularization
J Geiping, M Goldblum, G Somepalli, R Shwartz-Ziv, T Goldstein, ...
arXiv preprint arXiv:2210.06441, 2022
412022
Reverse engineering self-supervised learning
I Ben-Shaul, R Shwartz-Ziv, T Galanti, S Dekel, Y LeCun
Advances in Neural Information Processing Systems 36, 58324-58345, 2023
392023
Neural correlates of learning pure tones or natural sounds in the auditory cortex
I Maor, R Shwartz-Ziv, L Feigin, Y Elyada, H Sompolinsky, A Mizrahi
Frontiers in neural circuits 13, 82, 2020
39*2020
Attentioned convolutional LSTM inpainting network for anomaly detection in videos
R Shwartz-Ziv, I Ben-Ari
NIPS 2018 Workshop on Systems for ML, 2018
20*2018
The entropy enigma: Success and failure of entropy minimization
O Press, R Shwartz-Ziv, Y LeCun, M Bethge
Forty-first International Conference on Machine Learning (ICML 2024), 2024
162024
Simplifying neural network training under class imbalance
R Shwartz-Ziv, M Goldblum, Y Li, CB Bruss, AG Wilson
Advances in Neural Information Processing Systems 36, 35218-35245, 2023
16*2023
An information theory perspective on variance-invariance-covariance regularization
R Shwartz-Ziv, R Balestriero, K Kawaguchi, TGJ Rudner, Y LeCun
Advances in Neural Information Processing Systems 36, 33965-33998, 2023
13*2023
Does representation matter? exploring intermediate layers in large language models
O Skean, MR Arefin, Y LeCun, R Shwartz-Ziv
arXiv preprint arXiv:2412.09563, 2024
92024
Variance-covariance regularization improves representation learning
J Zhu, K Evtimova, Y Chen, R Shwartz-Ziv, Y LeCun
arXiv preprint arXiv:2306.13292, 2023
92023
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–20