67 citations · 419 across the 35 of their papers we have counts for
4 papers · 1 filter
How benign is benign overfitting?
Amartya Sanyal, Puneet K Dokania, Varun Kanade +1
We investigate two causes for adversarial vulnerability in deep neural networks: bad data and (poorly) trained models. When trained with SGD, deep neural networks essentially achie…
Lottery Tickets in Linear Models: An Analysis of Iterative Magnitude Pruning
Bryn Elesedy, Varun Kanade, Yee Whye Teh
We analyse the pruning procedure behind the lottery ticket hypothesis arXiv:1803.03635v5, iterative magnitude pruning (IMP), when applied to linear models trained by gradient flow.…
Differentiable Causal Backdoor Discovery
Limor Gultchin, Matt J. Kusner, Varun Kanade +1
Discovering the causal effect of a decision is critical to nearly all forms of decision-making. In particular, it is a key quantity in drug development, in crafting government poli…
The Statistical Complexity of Early-Stopped Mirror Descent
Tomas Vaškevičius, Varun Kanade, Patrick Rebeschini
Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the sta…