104 citations · 374 across the 40 of their papers we have counts for
5 papers · 2 filters
A geometric interpretation of stochastic gradient descent using diffusion metrics
R. Fioresi, P. Chaudhari, S. Soatto
Stochastic gradient descent (SGD) is a key ingredient in the training of deep neural networks and yet its geometrical significance appears elusive. We study a deterministic model i…
Directional Adversarial Training for Cost Sensitive Deep Learning Classification Applications
Matteo Terzi, Gian Antonio Susto, Pratik Chaudhari
In many real-world applications of Machine Learning it is of paramount importance not only to provide accurate predictions, but also to ensure certain levels of robustness. Adversa…
Meta-Q-Learning
Rasool Fakoor, Pratik Chaudhari, Stefano Soatto +1
This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learnin…
A Baseline for Few-Shot Image Classification
Guneet S. Dhillon, Pratik Chaudhari, Avinash Ravichandran +1
Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current sta…
P3O: Policy-on Policy-off Policy Optimization
Rasool Fakoor, Pratik Chaudhari, Alexander J. Smola
On-policy reinforcement learning (RL) algorithms have high sample complexity while off-policy algorithms are difficult to tune. Merging the two holds the promise to develop efficie…