← Authors

Christos Tzamos

41 papers · 2017–2025 · 6 conferences · across top CS/AI conferences

Achievements

πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (8) πŸ—ΊοΈ Taxonomy Completionist (11) 🌈 Renaissance Researcher (7) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (15) 🀝 Dynamic Duo (16) πŸ† Keyword Champion (2) πŸ† Grand Slam πŸ”¬ Deep Specialist (11) πŸ’Ž Century Club (41) ⚑ Prolific Year (5) πŸ—ƒοΈ Keyword Collector (158) πŸ”₯ Unstoppable (9)

Conferences

COLT (15) NIPS (13) ICML (10) AAAI (1) AISTATS (1) ICLR (1)

Top co-authors

Ilias Diakonikolas (16) Vasilis Kontonis (15) Nikos Zarifis (8) Mingchen Ma (6) Dimitris Fotakis (5) Alkis Kalavasis (5) Jong Ho Park (4) Evangelia Gergatsouli (4) Manolis Zampetakis (4) Constantinos Daskalakis (3)

Research topics

Optimization (1)

Keywords

massart noise (6) stochastic optimization (5) halfspace learning (4) stochastic gradient descent (4) pac learning (4) adversarial label noise (4) maximum likelihood estimation (3) log-concave distribution (3) sample complexity (3) noisy label (2) query complexity (2) online algorithm (2) approximation algorithm (2) non-convex optimization (2) active learning (2) agnostic learning (2) expectation maximization (2) combinatorial optimization (2) online learning (2) statistical query (2)

Papers

Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise ICML 2025
Online Linear Classification with Massart Noise ICML 2025
Oracle efficient truncated statistics ICLR 2025
Fast Co-Training under Weak Dependence via Stream-Based Active Learning ICML 2024
Active Classification with Few Queries under Misspecification NIPS 2024
Optimization Can Learn Johnson Lindenstrauss Embeddings NIPS 2024
Contextual Pandora’s Box AAAI 2024
Weitzman's Rule for Pandora's Box with Correlations NIPS 2023
Self-Directed Linear Classification COLT 2023
Buying Information for Stochastic Optimization ICML 2023
Distribution-Independent Regression for Generalized Linear Models with Oblivious Corruptions COLT 2023
Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method NIPS 2023
First Order Stochastic Optimization with Oblivious Noise NIPS 2023
The Gain from Ordering in Online Learning NIPS 2023
Linear Label Ranking with Bounded Noise NIPS 2022
Perfect Sampling from Pairwise Comparisons NIPS 2022
Learning a Single Neuron with Adversarial Label Noise via Gradient Descent COLT 2022
Clustering with Queries under Semi-Random Noise COLT 2022
Learning General Halfspaces with Adversarial Label Noise via Online Gradient Descent ICML 2022
Online Learning for Min Sum Set Cover and Pandora’s Box ICML 2022
Learning Online Algorithms with Distributional Advice ICML 2021
On Robust Mean Estimation under Coordinate-level Corruption ICML 2021
A Statistical Taylor Theorem and Extrapolation of Truncated Densities COLT 2021
Agnostic Proper Learning of Halfspaces under Gaussian Marginals COLT 2021
Boosting in the Presence of Massart Noise COLT 2021
Efficient Algorithms for Learning from Coarse Labels COLT 2021
ReLU Regression with Massart Noise NIPS 2021
Forster Decomposition and Learning Halfspaces with Noise NIPS 2021
Learning Halfspaces with Massart Noise Under Structured Distributions COLT 2020
Optimal Private Median Estimation under Minimal Distributional Assumptions NIPS 2020
Efficient Parameter Estimation of Truncated Boolean Product Distributions COLT 2020
Non-Convex SGD Learns Halfspaces with Adversarial Label Noise NIPS 2020
Black-Box Methods for Restoring Monotonicity ICML 2020
Computationally and Statistically Efficient Truncated Regression COLT 2019
Distribution-Independent PAC Learning of Halfspaces with Massart Noise NIPS 2019
Learning to Prune: Speeding up Repeated Computations COLT 2019
Bootstrapping EM via Power EM and Convergence in the Naive Bayes Model AISTATS 2018
Actively Avoiding Nonsense in Generative Models COLT 2018
Certified Computation from Unreliable Datasets COLT 2018
Ten Steps of EM Suffice for Mixtures of Two Gaussians COLT 2017
Improving Viterbi is Hard: Better Runtimes Imply Faster Clique Algorithms ICML 2017