Search Results for author:
Found 10 papers, 7 papers with code
DiffAIL: Diffusion Adversarial Imitation Learning
To address this issue, we propose a method named diffusion adversarial imitation learning (DiffAIL), which introduces the diffusion model into the AIL framework.
Towards Understanding Generalization of Macro-AUC in Multi-label Learning
We theoretically identify a critical factor of the dataset affecting the generalization bounds: \emph{the label-wise class imbalance}.
Revisiting Discriminative vs. Generative Classifiers: Theory and Implications
Theoretically, the paper considers the surrogate loss instead of the zero-one loss in analyses and generalizes the classical results from binary cases to multiclass ones.
Deep Ensemble as a Gaussian Process Approximate Posterior
In this way, we relate DE to Bayesian inference to enjoy reliable Bayesian uncertainty.
Deep Ensemble as a Gaussian Process Posterior
Deep Ensemble (DE) is a flexible, feasible, and effective alternative to Bayesian neural networks (BNNs) for uncertainty estimation in deep learning.
On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms
Finally, our theoretical results are confirmed by experiments on several numerical benchmarks as well as adversarial attacks.
Stability and Generalization of Bilevel Programming in Hyperparameter Optimization
Our results can explain some mysterious behaviours of the bilevel programming in practice, for instance, overfitting to the validation set.
Rethinking and Reweighting the Univariate Losses for Multi-Label Ranking: Consistency and Generalization
Our results show that learning algorithms with the consistent univariate loss have an error bound of $O(c)$ ($c$ is the number of labels), while algorithms with the inconsistent pairwise loss depend on $O(\sqrt{c})$ as shown in prior work.
Multi-label classification: do Hamming loss and subset accuracy really conflict with each other?
On the other hand, when directly optimizing SA with its surrogate loss, it has learning guarantees that depend on $O(\sqrt{c})$ for both HL and SA measures.
Joint Ranking SVM and Binary Relevance with Robust Low-Rank Learning for Multi-Label Classification
RBRL inherits the ranking loss minimization advantages of Rank-SVM, and thus overcomes the disadvantages of BR suffering the class-imbalance issue and ignoring the label correlations.
