v1v2v3 (latest)

Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory

1 October 2019

Papers citing "Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory"

20 / 20 papers shown

Title
Just How Flexible are Neural Networks in Practice? Ravid Shwartz-Ziv Micah Goldblum Arpit Bansal C. Bayan Bruss Yann LeCun Andrew Gordon Wilson 106 5 0 17 Jun 2024
Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape Kedar Karhadkar Michael Murray Hanna Tseran Guido Montúfar 73 8 0 31 May 2023
Winning the Lottery Ahead of Time: Efficient Early Network Pruning John Rachwan Daniel Zügner Bertrand Charpentier Simon Geisler Morgane Ayle Stephan Günnemann 86 26 0 21 Jun 2022
Understanding Deep Learning via Decision Boundary Shiye Lei Fengxiang He Yancheng Yuan Dacheng Tao 76 14 0 03 Jun 2022
Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training? J. Mok Byunggook Na Ji-Hoon Kim Dongyoon Han Sungroh Yoon AAML 103 25 0 28 Mar 2022
On the Omnipresence of Spurious Local Minima in Certain Neural Network Training Problems C. Christof Julia Kowalczyk 92 8 0 23 Feb 2022
Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models Liam H. Fowl Jonas Geiping W. Czaja Micah Goldblum Tom Goldstein FedML 149 149 0 25 Oct 2021
An Unconstrained Layer-Peeled Perspective on Neural Collapse Wenlong Ji Yiping Lu Yiliang Zhang Zhun Deng Weijie J. Su 238 87 0 06 Oct 2021
Stochastic Training is Not Necessary for Generalization Jonas Geiping Micah Goldblum Phillip E. Pope Michael Moeller Tom Goldstein 188 76 0 29 Sep 2021
A linearized framework and a new benchmark for model selection for fine-tuning Aditya Deshpande Alessandro Achille Avinash Ravichandran Hao Li Luca Zancato Charless C. Fowlkes Rahul Bhotika Stefano Soatto Pietro Perona ALM 191 49 0 29 Jan 2021
Recent advances in deep learning theory Fengxiang He Dacheng Tao AI4CE 138 51 0 20 Dec 2020
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent William Merrill Vivek Ramanujan Yoav Goldberg Roy Schwartz Noah A. Smith AI4CE 103 36 0 19 Oct 2020
Pareto Probing: Trading Off Accuracy for Complexity Tiago Pimentel Naomi Saphra Adina Williams Ryan Cotterell 101 60 0 05 Oct 2020
Ramifications of Approximate Posterior Inference for Bayesian Deep Learning in Adversarial and Out-of-Distribution Settings John Mitros A. Pakrashi Brian Mac Namee UQCV 114 2 0 03 Sep 2020
Predicting Training Time Without Training Luca Zancato Alessandro Achille Avinash Ravichandran Rahul Bhotika Stefano Soatto 156 24 0 28 Aug 2020
Finite Versus Infinite Neural Networks: an Empirical Study Jaehoon Lee S. Schoenholz Jeffrey Pennington Ben Adlam Lechao Xiao Roman Novak Jascha Narain Sohl-Dickstein 118 214 0 31 Jul 2020
Inverting Gradients -- How easy is it to break privacy in federated learning? Jonas Geiping Hartmut Bauermeister Hannah Dröge Michael Moeller FedML 174 1,241 0 31 Mar 2020
Piecewise linear activations substantially shape the loss surfaces of neural networks Fengxiang He Bohan Wang Dacheng Tao ODL 100 30 0 27 Mar 2020
Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks Micah Goldblum Steven Reich Liam H. Fowl Renkun Ni Valeriia Cherepanova Tom Goldstein SSL OffRL 120 75 0 17 Feb 2020
Four Things Everyone Should Know to Improve Batch Normalization Cecilia Summers M. Dinneen 85 52 0 09 Jun 2019