Search Results for author:
Found 10 papers, 3 papers with code
Semi-Supervised Semantic Segmentation under Label Noise via Diverse Learning Groups
Each learning group consists of a teacher network, a student network and a novel filter module.
Confident Sinkhorn Allocation for Pseudo-Labeling
CSA outperforms the current state-of-the-art in this practically important area of semi-supervised learning.
A Law of Robustness for Weight-bounded Neural Networks
Our result coincides with that conjectured in (Bubeck et al., 2020) for two-layer networks under the assumption of bounded weights.
Regularized Policies are Reward Robust
Entropic regularization of policies in Reinforcement Learning (RL) is a commonly used heuristic to ensure that the learned policy explores the state-space sufficiently before overfitting to a local optimal policy.
Fair Densities via Boosting the Sufficient Statistics of Exponential Families
Furthermore, when the weak learners are specified to be decision trees, the sufficient statistics of the learned distribution can be examined to provide clues on sources of (un)fairness.
Optimal Continual Learning has Perfect Memory and is NP-hard
Continual Learning (CL) algorithms incrementally learn a predictor or representation across multiple sequentially observed tasks.
Distributional Robustness with IPMs and links to Regularization and GANs
Our main result shows that DRO under \textit{any} choice of IPM corresponds to a family of regularization penalties, which recover and improve upon existing results in the setting of MMD and Wasserstein distances.
A Primal-Dual link between GANs and Autoencoders
First, we find that the $f$-GAN and WAE objectives partake in a primal-dual relationship and are equivalent under some assumptions, which then allows us to explicate the success of WAE.
Adversarial Networks and Autoencoders: The Primal-Dual Relationship and Generalization Bounds
First, we find that the $f$-GAN and WAE objectives partake in a primal-dual relationship and are equivalent under some assumptions, which then allows us to explicate the success of WAE.
Integral Privacy for Sampling
Privacy enforces an information theoretic barrier on approximation, and we show how to reach this barrier with guarantees on the approximation of the target non private density.
