activity
20152020
most citedBiased Importance Sampling for Deep Neural Network Training

48 citations · 71 across the 4 of their papers we have counts for

collaborators

15 papers

cs.LG2020

Rethinking the Role of Gradient-Based Attribution Methods for Model Interpretability

Suraj Srinivas, Francois Fleuret

Current methods for the interpretability of discriminative deep neural networks commonly rely on the model's input-gradients, i.e., the gradients of the output logits w.r.t. the in…

cs.LG2019

Optimizer Benchmarking Needs to Account for Hyperparameter Tuning

Prabhu Teja Sivaprasad, Florian Mai, Thijs Vogels +2

The performance of optimizers, particularly in deep learning, depends considerably on their chosen hyperparameter configuration. The efficacy of optimizers is often studied under n…

cs.LG2019

Full-Gradient Representation for Neural Network Visualization

Suraj Srinivas, Francois Fleuret

We introduce a new tool for interpreting neural net responses, namely full-gradients, which decomposes the neural net response into input sensitivity and per-neuron sensitivity com…

stat.ML2019

Reducing Noise in GAN Training with Variance Reduced Extragradient

Tatjana Chavdarova, Gauthier Gidel, François Fleuret +1

We study the effect of the stochastic gradient noise on the training of generative adversarial networks (GANs) and show that it can prevent the convergence of standard game optimiz…

cs.CV2018

Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching

Stepan Tulyakov, Anton Ivanov, Francois Fleuret

End-to-end deep-learning networks recently demonstrated extremely good perfor- mance for stereo matching. However, existing networks are difficult to use for practical applications…

cs.LG2018

Not All Samples Are Created Equal: Deep Learning with Importance Sampling

Angelos Katharopoulos, François Fleuret

Deep neural network training spends most of the computation on examples that are properly handled, and could be ignored. We propose to mitigate this phenomenon with a principled im…