← Authors

Daniel Hsu

48 papers · 2011–2025 · 11 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (11) πŸƒ Academic Marathon (14) 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (11) 🌈 Renaissance Researcher (10) πŸ—ΊοΈ Taxonomy Completionist (19) 🧭 Keyword Pioneer 🌱 Topic Pioneer πŸ† Keyword Champion (2) πŸ—ƒοΈ Keyword Collector (172) ⚑ Prolific Year (6) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter πŸ’Ž Century Club (48) πŸ”₯ Unstoppable (12) ❓ The Questioner (2)

Conferences

COLT (10) JMLR (10) ICML (9) AISTATS (5) ALT (4) EMNLP (4) IJCNLP (2) ACL (1) ICLR (1) NAACL (1) NIPS (1)

Top co-authors

Animashree Anandkumar (6) Giannis Karamanolakis (6) Luis Gravano (6) Sham M. Kakade (4) Matus Telgarsky (4) Christopher Tosh (3) Rishabh Dudeja (3) Samuel Deng (3) Rong Ge (3) Sham Kakade (3)

Research topics

Education (1)

Keywords

sample complexity (6) tensor decomposition (5) spectral method (4) linear regression (4) online learning (3) weakly supervised learning (3) least square (3) representation learning (3) aspect detection (3) regret bound (2) stochastic block model (2) robust estimation (2) linear classifier (2) support vector machine (2) dirichlet distribution (2) community detection (2) opinion mining (2) contrastive learning (2) text classification (2) topic modeling (2)

Papers

Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence AISTATS 2025
Learning Compositional Functions with Transformers from Easy-to-Hard Data COLT 2025
Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot ICML 2024
Multi-group Learning for Hierarchical Groups ICML 2024
Group-wise oracle-efficient algorithms for online multi-group learning NIPS 2024
On the sample complexity of parameter estimation in logistic regression with normal design COLT 2024
Transformers, parallel computation, and logarithmic depth ICML 2024
Algorithmic Learning Theory 2024: Preface ALT 2024
Simple and near-optimal algorithms for hidden stratification and multi-group learning ICML 2022
Learning Tensor Representations for Meta-Learning AISTATS 2022
Unbiased estimators for random design regression JMLR 2022
On the Approximation Power of Two-Layer Networks of Random ReLUs COLT 2021
Quantifying the Effects of COVID-19 on Restaurant Reviews NAACL 2021
On the proliferation of support vectors in high dimensions AISTATS 2021
Contrastive Estimation Reveals Topic Posterior Information to Linear Models JMLR 2021
Classification vs regression in overparameterized regimes: Does the loss function matter? JMLR 2021
Contrastive learning, multi-view redundancy, and linear models ALT 2021
Statistical Query Lower Bounds for Tensor PCA JMLR 2021
Generalization bounds via distillation ICLR 2021
Detecting Foodborne Illness Complaints in Multiple Languages Using English Annotations Only EMNLP 2020
Diameter-based Interactive Structure Discovery AISTATS 2020
Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher EMNLP 2020
Weakly Supervised Attention Networks for Fine-Grained Opinion Mining and Public Health EMNLP 2019
Conference on Learning Theory 2019: Preface COLT 2019
A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization ICML 2019
Teaching a black-box learner ICML 2019
Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training IJCNLP 2019
Kernel Approximation Methods for Speech Recognition JMLR 2019
Attribute-efficient learning of monomials over highly-correlated variables ALT 2019
Correcting the bias in least squares regression with volume-rescaled sampling AISTATS 2019
Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training EMNLP 2019
Learning Single-Index Models in Gaussian Space COLT 2018
Correspondence retrieval COLT 2017
Parameter identification in Markov chain choice models ALT 2017
Loss Minimization and Parameter Estimation with Heavy Tails JMLR 2016
Learning Sparse Low-Threshold Linear Classifiers JMLR 2015
Model-based Word Embeddings from Decompositions of Count Matrices ACL 2015
When Are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity JMLR 2015
Model-based Word Embeddings from Decompositions of Count Matrices IJCNLP 2015
Heavy-tailed regression with a generalized median-of-means ICML 2014
A Tensor Approach to Learning Mixed Membership Community Models JMLR 2014
Tensor Decompositions for Learning Latent Variable Models JMLR 2014
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits ICML 2014
Learning Linear Bayesian Networks with Latent Variables ICML 2013
A Tensor Spectral Approach to Learning Mixed Membership Community Models COLT 2013
A Method of Moments for Mixture Models and Hidden Markov Models COLT 2012
Random Design Analysis of Ridge Regression COLT 2012
Sample Complexity Bounds for Differentially Private Learning COLT 2011