Masashi Sugiyama

70

Papers

906

Total Citations

Papers (70)

Positive-Unlabeled Learning with Non-Negative Risk Estimator

NeurIPS 2017arXiv

Learning from Complementary Labels

NeurIPS 2017arXiv

Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning

NeurIPS 2016arXiv

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

Expectation Propagation for t-Exponential Family Using q-Algebra

NeurIPS 2017arXiv

Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation

Towards Out-of-Modal Generalization without Instance-level Modal Correspondence

The adaptive complexity of parallelized log-concave sampling

Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical

Generative Local Metric Learning for Kernel Regression

Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training

Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought

On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective

Instance-Dependent Label-Noise Learning With Manifold-Regularized Transition Matrix Estimation

Distribution Shift Matters for Knowledge Distillation with Webly Collected Images

Multi-Label Knowledge Distillation

Balancing Similarity and Complementarity for Federated Learning

Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning

Action-Agnostic Point-Level Supervision for Temporal Action Detection

Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit

The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models

Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization

A General Framework for Learning from Weak Supervision

Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift Adaptation

On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective

Binary Classification with Confidence Difference

Distributional Pareto-Optimal Multi-Objective Reinforcement Learning

Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization

Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation

Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems

Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning

Adapting to Continuous Covariate Shift via Online Density Ratio Estimation

Online (Multinomial) Logistic Bandit: Improved Regret and Constant Computation Cost

Imitation Learning from Vague Feedback

Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection

Convex Formulation for Learning from Positive and Unlabeled Data

Structure Learning of Partitioned Markov Networks

Learning Discrete Representations via Information Maximizing Self-Augmented Training

Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data

Classification from Pairwise Similarity and Unlabeled Data

Does Distributionally Robust Supervised Learning Give Robust Classifiers?

Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model

On Symmetric Losses for Learning from Corrupted Labels

Classification from Positive, Unlabeled and Biased Negative Data

Complementary-Label Learning for Arbitrary Losses and Models

Imitation Learning from Imperfect Demonstration

How does Disagreement Help Generalization against Label Corruption?

Uplift Modeling from Separate Labels

Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks

Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces

Co-teaching: Robust training of deep neural networks with extremely noisy labels

Masking: A New Perspective of Noisy Supervision

Binary Classification from Positive-Confidence Data

On the Calibration of Multiclass Classification with Rejection

Uncoupled Regression from Pairwise Comparison Data

Are Anchor Points Really Indispensable in Label-Noise Learning?

Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators

Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning

Part-dependent Label Noise: Towards Instance-dependent Label Noise

Learning from Aggregate Observations

NeurIPS 2020arXiv

Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring

Provably Consistent Partial-Label Learning

Rethinking Importance Weighting for Deep Learning under Distribution Shift

Loss function based second-order Jensen inequality and its application to particle variational inference

Probabilistic Margins for Instance Reweighting in Adversarial Training

Generalizing Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses

Learning Contrastive Embedding in Low-Dimensional Space

Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks

Adapting to Online Label Shift with Provable Guarantees

Synergy-of-Experts: Collaborate to Improve Adversarial Robustness