Dimitris Papailiopoulos

22
Papers
207
Total Citations
1
Affiliations

Affiliations

University of Wisconsin-Madison

Papers (22)

Teaching Arithmetic to Small Transformers

ICLR 2024
117
citations

Cyclades: Conflict-free Asynchronous Machine Learning

NeurIPS 2016arXiv
64
citations

From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data

ICLR 2025
19
citations

Extrapolation by Association: Length Generalization Transfer In Transformers

NeurIPS 2025arXiv
7
citations

Orthogonal NMF through Subspace Exploration

NeurIPS 2015
0
citations

Parallel Correlation Clustering on Big Graphs

NeurIPS 2015
0
citations

CHAI: Clustered Head Attention for Efficient LLM Inference

ICML 2024
0
citations

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks

ICML 2024
0
citations

Sparse PCA via Bipartite Matchings

NeurIPS 2015
0
citations

Rare Gems: Finding Lottery Tickets at Initialization

NeurIPS 2022
0
citations

Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning

NeurIPS 2023
0
citations

Stability and Generalization of Learning Algorithms that Converge to Global Optima

ICML 2018
0
citations

DRACO: Byzantine-resilient Distributed Training via Redundant Gradients

ICML 2018
0
citations

Does Data Augmentation Lead to Positive Margin?

ICML 2019
0
citations

ATOMO: Communication-efficient Learning via Atomic Sparsification

NeurIPS 2018
0
citations

The Effect of Network Width on the Performance of Large-batch Training

NeurIPS 2018
0
citations

DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation

NeurIPS 2019
0
citations

Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient

NeurIPS 2020
0
citations

Bad Global Minima Exist and SGD Can Reach Them

NeurIPS 2020
0
citations

Attack of the Tails: Yes, You Really Can Backdoor Federated Learning

NeurIPS 2020
0
citations

An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks

NeurIPS 2021
0
citations

LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning Tasks

NeurIPS 2022
0
citations