Alkis Kalavasis

23 papers · 2020–2026 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+9 more ↓

🗺️ Taxonomy Completionist (42) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

👑 Triple Crown 🔬 Deep Specialist (11) 🌈 Renaissance Researcher (6) 🔥 Unstoppable · Bronze ❓ The Questioner (3) ⚡ Prolific Year · Productive 💎 Century Club · Bronze 📈 Trend Setter 🗃️ Keyword Collector (118)

Venues

NeurIPS (8) COLT (7) ICML (4) AISTATS (2) ALT (1) ICLR (1)

Top co-authors

Grigoris Velegkas (9) Dimitris Fotakis (8) Amin Karbasi (8) Christos Tzamos (5) Anay Mehrotra (5) Manolis Zampetakis (3) Vasilis Kontonis (3) Felix Zhou (3) Steve Hanneke (2) Konstantinos Stavropoulos (2)

Research topics

Machine Learning (22) Optimization & Theory (16) Core Methods (10) Learning Types (7) Mathematics & Optimization (6) Artificial Intelligence (5) Optimization (5) Core AI (4) Deep Learning (3) Knowledge & Reasoning (2) Application Areas (2) Mathematics (2) Models (2) Probability (2) Reasoning (2)

Keywords

sample complexity (7) pac learning (3) differential privacy (3) online learning (2) linear regression (2) causal inference (2) total variation distance (2) mallows model (2) pairwise comparison (2) average treatment effect (2) algorithmic stability (2) learning rate (2) stochastic gradient descent (2) label ranking (2) neural network (2) adversarial machine learning (1) large margin (1) parameter estimation (1) model security (1) policy gradient (1)

Papers

Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases (Extended Abstract) COLT 2026 DDPM Score Matching and Distribution Learning (Extended Abstract) COLT 2026 On Characterizations for Language Generation: Interplay of Hallucinations, Breadth, and Stability ALT 2026 Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion ICML 2025 What Makes Treatment Effects Identifiable? Characterizations and Estimators Beyond Unconfoundedness (Extended Abstract) COLT 2025 Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models NeurIPS 2024 On the Computational Landscape of Replicable Learning NeurIPS 2024 Replicable Learning of Large-Margin Halfspaces ICML 2024 Smaller Confidence Intervals From IPW Estimators via Data-Dependent Coarsening (Extended Abstract) COLT 2024 Universal Rates for Regression: Separations between Cut-Off and Absolute Loss COLT 2024 Optimal Learners for Realizable Regression: PAC Learning and Online Learning NeurIPS 2023 Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method NeurIPS 2023 Replicable Bandits ICLR 2023 Statistical Indistinguishability of Learning Algorithms ICML 2023 Differentially Private Regression with Unbounded Covariates AISTATS 2022 Label Ranking through Nonparametric Regression ICML 2022 Learning and Covering Sums of Independent Random Variables with Unbounded Support NeurIPS 2022 Linear Label Ranking with Bounded Noise NeurIPS 2022 Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes NeurIPS 2022 Perfect Sampling from Pairwise Comparisons NeurIPS 2022 Aggregating Incomplete and Noisy Rankings AISTATS 2021 Efficient Algorithms for Learning from Coarse Labels COLT 2021 Efficient Parameter Estimation of Truncated Boolean Product Distributions COLT 2020