Alkis Kalavasis
21 papers · 2020–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Academic Marathon (5) π Conference Polyglot (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (14)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(28)
π
Interdisciplinary Bridge
π
Triple Crown
β‘
Prolific Year
(5)
ποΈ
Keyword Collector
(82)
π₯
Unstoppable
(6)
π
Century Club
(20)
β
The Questioner
(2)
Conferences
NIPS (8)
COLT (5)
ICML (4)
AISTATS (2)
ALT (1)
ICLR (1)
Top co-authors
Research topics
Keywords
sample complexity
(5)
differential privacy
(3)
pac learning
(3)
algorithmic stability
(2)
neural network
(2)
online learning
(2)
label ranking
(2)
total variation distance
(2)
pairwise comparison
(2)
learning rate
(2)
model security
(1)
adversarial machine learning
(1)
stochastic gradient descent
(1)
covariance estimation
(1)
parameter estimation
(1)
policy gradient
(1)
learning theory
(1)
vc dimension
(1)
statistical query
(1)
multiclass classification
(1)
Papers
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
Replicable Learning of Large-Margin Halfspaces
ICML 2024
Smaller Confidence Intervals From IPW Estimators via Data-Dependent Coarsening (Extended Abstract)
COLT 2024
Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
NIPS 2024
On the Computational Landscape of Replicable Learning
NIPS 2024
Universal Rates for Regression: Separations between Cut-Off and Absolute Loss
COLT 2024
Optimal Learners for Realizable Regression: PAC Learning and Online Learning
NIPS 2023
Statistical Indistinguishability of Learning Algorithms
ICML 2023
Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method
NIPS 2023
Replicable Bandits
ICLR 2023
Linear Label Ranking with Bounded Noise
NIPS 2022
Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes
NIPS 2022
Learning and Covering Sums of Independent Random Variables with Unbounded Support
NIPS 2022
Perfect Sampling from Pairwise Comparisons
NIPS 2022
Differentially Private Regression with Unbounded Covariates
AISTATS 2022
Label Ranking through Nonparametric Regression
ICML 2022
Efficient Algorithms for Learning from Coarse Labels
COLT 2021
Aggregating Incomplete and Noisy Rankings
AISTATS 2021
Efficient Parameter Estimation of Truncated Boolean Product Distributions
COLT 2020