Search Results for author:
Found 7 papers, 4 papers with code
Direct Preference-based Policy Optimization without Reward Modeling
We apply our algorithm to offline RL tasks with actual human preference labels and show that our algorithm outperforms or is on par with the existing PbRL methods.
Optimal channel selection with discrete QCQP
We first show the greedy approach of recent channel pruning methods ignores the inherent quadratic coupling between channels in the neighboring layers and cannot safely remove inactive weights during the pruning procedure.
Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks
However, the vulnerability of neural networks against adversarial attacks poses a serious threat to the people affected by these systems.
Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble
However, prior methods typically require accurate estimation of the behavior policy or sampling from OOD data points, which themselves can be a non-trivial problem.
Ranked #1 on
Gym halfcheetah-random
on D4RL
Succinct Network Channel and Spatial Pruning via Discrete Variable QCQP
Reducing the heavy computational cost of large convolutional neural networks is crucial when deploying the networks to resource-constrained environments.
Exploiting Safe Spots in Neural Networks for Preemptive Robustness and Out-of-Distribution Detection
Recent advances on adversarial defense mainly focus on improving the classifier’s robustness against adversarially perturbed inputs.
Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization
Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers.
