Search Results for author:
Found 6 papers, 4 papers with code
Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning
Inspired by the recent success of learning robust models with unlabeled data, we explore a new robustness-aware CIL setting, where the learned adversarial robustness has to resist forgetting and be transferred as new tasks come in continually.
Optimizer Amalgamation
Selecting an appropriate optimizer for a given problem is of major interest for researchers and practitioners.
How Much Automation Does a Data Scientist Want?
There is an active research thread in AI, \autoai, that aims to develop systems for automating end-to-end the DS/ML Lifecycle.
Training Stronger Baselines for Learning to Optimize
Learning to optimize (L2O) has gained increasing attention since classical optimizers require laborious problem-specific design and hyperparameter tuning.
Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning
We conduct extensive experiments to demonstrate that the proposed framework achieves large performance margins (eg, 3. 83% on robust accuracy and 1. 3% on standard accuracy, on the CIFAR-10 dataset), compared with the conventional end-to-end adversarial training baseline.
Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization
As application demands for zeroth-order (gradient-free) optimization accelerate, the need for variance reduced and faster converging approaches is also intensifying.
