Nikos Karampatziakis
11 papers · 2010–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (15) π Conference Polyglot (3)
πΊοΈ
Taxonomy Completionist
(15)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π±
Topic Pioneer
π
Keyword Champion
ποΈ
Keyword Collector
(65)
π
Trend Setter
π
Century Club
(11)
π
Conference Pioneer
Conferences
ICML (6)
NIPS (4)
ICLR (1)
Top co-authors
Keywords
contextual bandit
(2)
multiclass classification
(2)
off-policy evaluation
(2)
binary classification
(1)
distributed learning
(1)
feature extraction
(1)
policy optimization
(1)
text generation
(1)
language modeling
(1)
supervised learning
(1)
gradient descent
(1)
binary analysis
(1)
empirical risk minimization
(1)
uncertainty quantification
(1)
conformal prediction
(1)
multi-class classification
(1)
machine learning
(1)
data reduction
(1)
excess risk
(1)
active learning
(1)
Papers
Active, anytime-valid risk controlling prediction sets
NIPS 2024
LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models
ICLR 2024
Meet in the Middle: A New Pre-training Paradigm
NIPS 2023
Off-Policy Confidence Sequences
ICML 2021
Empirical Likelihood for Contextual Bandits
NIPS 2020
Logarithmic Time One-Against-Some
ICML 2017
Gradient Coding: Avoiding Stragglers in Distributed Learning
ICML 2017
Least Squares Revisited: Scalable Approaches for Multi-class Prediction
ICML 2014
Discriminative Features via Generalized Eigenvectors
ICML 2014
Loss-Proportional Subsampling for Subsequent ERM
ICML 2013
Static Analysis of Binary Executables Using Structural SVMs
NIPS 2010