CHRISTOS THRAMPOULIDIS
36 papers · 2015–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
π Conference Polyglot (9) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (13) π§ Keyword Pioneer π Academic Marathon (10)
π
Academic Marathon
(10)
π
Cross-Pollinator
(6)
π
Renaissance Researcher
(7)
π¬
Deep Specialist
(12)
π
Grand Slam
π
Keyword Champion
(2)
ποΈ
Keyword Collector
(148)
β‘
Prolific Year
(7)
π
Century Club
(35)
π
Trend Setter
π₯
Unstoppable
(7)
π
Conference Pioneer
Conferences
NIPS (12)
AAAI (5)
AISTATS (5)
ICLR (4)
ICML (4)
CVPR (2)
ACL (1)
COLT (1)
JMLR (1)
L4DC (1)
Top co-authors
Keywords
safety constraint
(5)
regret bound
(5)
gradient descent
(5)
multi-armed bandit
(4)
support vector machine
(4)
upper confidence bound
(3)
stochastic optimization
(3)
generalization bound
(3)
implicit bia
(3)
cross-entropy loss
(3)
federated learning
(3)
neural network
(3)
class imbalance
(3)
neural collapse
(2)
loss function
(2)
high-dimensional analysis
(2)
algorithmic stability
(2)
signal recovery
(2)
multiclass classification
(2)
logistic regression
(2)
Papers
For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs
ACL 2026
Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation
ICML 2025
Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods
ICLR 2025
DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models
ICLR 2025
Memorization Capacity of Multi-Head Attention in Transformers
ICLR 2024
Implicit Optimization Bias of Next-token Prediction in Linear Models
NIPS 2024
Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective
AAAI 2024
Engineering the Neural Collapse Geometry of Supervised-Contrastive Loss (Student Abstract)
AAAI 2024
Generalization and Stability of Interpolating Neural Networks with Minimal Width
JMLR 2024
Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning
CVPR 2024
Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching
ICLR 2024
On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data
AISTATS 2023
Fast Convergence in Learning Two-Layer Neural Networks with Separable Data
AAAI 2023
On the Role of Attention in Prompt-tuning
ICML 2023
On Generalization of Decentralized Learning with Separable Data
AISTATS 2023
BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization
NIPS 2023
FedNest: Federated Bilevel, Minimax, and Compositional Optimization
ICML 2022
Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently
NIPS 2022
Imbalance Trouble: Revisiting Neural-Collapse Geometry
NIPS 2022
Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions
AISTATS 2021
Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation
NIPS 2021
AutoBalance: Optimized Loss Functions for Imbalanced Data
NIPS 2021
Label-Imbalanced and Group-Sensitive Classification under Overparameterization
NIPS 2021
Decentralized Multi-Agent Linear Bandits with Safety Constraints
AAAI 2021
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
AAAI 2021
Safe Reinforcement Learning with Linear Function Approximation
ICML 2021
UCB-based Algorithms for Multinomial Logistic Regression Bandits
NIPS 2021
Sharp Asymptotics and Optimal Performance for Inference in Binary Models
AISTATS 2020
Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
NIPS 2020
Stage-wise Conservative Linear Bandits
NIPS 2020
Regret Bound for Safe Gaussian Process Bandit Optimization
L4DC 2020
Lifting high-dimensional non-linear models with Gaussian regressors
AISTATS 2019
Linear Stochastic Bandits Under Safety Constraints
NIPS 2019
Using Unknown Occluders to Recover Hidden Scenes
CVPR 2019
Regularized Linear Regression: A Precise Analysis of the Estimation Error
COLT 2015
LASSO with Non-linear Measurements is Equivalent to One With Linear Measurements
NIPS 2015