10 citations · 20 across the 15 of their papers we have counts for
17 papers
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
DeepCrossAttention: Supercharging Transformer Residual Connections
Mike Heddes, Adel Javanmard, Kyriakos Axiotis +3
Transformer networks have achieved remarkable success across diverse domains, leveraging a variety of architectural innovations, including residual connections. However, traditiona…
Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond
Kyriakos Axiotis, Vincent Cohen-Addad, Monika Henzinger +5
We study the data selection problem, whose aim is to select a small representative subset of data that can be used to efficiently train a machine learning model. We present a new d…
SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
Taisuke Yasuda, Kyriakos Axiotis, Gang Fu +2
Neural network pruning is a key technique towards engineering large yet scalable, interpretable, and generalizable models. Prior work on the subject has developed largely along two…
Greedy PIG: Adaptive Integrated Gradients
Kyriakos Axiotis, Sami Abu-al-haija, Lin Chen +2
Deep learning has become the standard approach for most machine learning tasks. While its impact is undeniable, interpreting the predictions of deep learning models from a human pe…
Performance of Regularization for Sparse Convex Optimization
Kyriakos Axiotis, Taisuke Yasuda
Despite widespread adoption in practice, guarantees for the LASSO and Group LASSO are strikingly lacking in settings beyond statistical problems, and these algorithms are usually c…
Gradient Descent Converges Linearly for Logistic Regression on Separable Data
Kyriakos Axiotis, Maxim Sviridenko
We show that running gradient descent with variable learning rate guarantees loss for the logistic regression objective, where the error decays…
Iterative Hard Thresholding with Adaptive Regularization: Sparser Solutions Without Sacrificing Runtime
Kyriakos Axiotis, Maxim Sviridenko
We propose a simple modification to the iterative hard thresholding (IHT) algorithm, which recovers asymptotically sparser solutions as a function of the condition number. When aim…
Faster Sparse Minimum Cost Flow by Electrical Flow Localization
Kyriakos Axiotis, Aleksander Mądry, Adrian Vladu
We give an time algorithm for minimum cost flow with capacities bounded by and costs bounded by . For sparse graphs with genera…
Decomposable Submodular Function Minimization via Maximum Flow
Kyriakos Axiotis, Adam Karczmarz, Anish Mukherjee +2
This paper bridges discrete and continuous optimization approaches for decomposable submodular function minimization, in both the standard and parametric settings. We provide impro…
Local Search Algorithms for Rank-Constrained Convex Optimization
Kyriakos Axiotis, Maxim Sviridenko
We propose greedy and local search algorithms for rank-constrained convex optimization, namely solving given a convex function $R…
Fast and Simple Modular Subset Sum
Kyriakos Axiotis, Arturs Backurs, Karl Bringmann +4
We revisit the Subset Sum problem over the finite cyclic group for some given integer . A series of recent works has provided near-optimal algorithms for this pro…
Sparse Convex Optimization via Adaptively Regularized Hard Thresholding
Kyriakos Axiotis, Maxim Sviridenko
The goal of Sparse Convex Optimization is to optimize a convex function under a sparsity constraint , where is the target number of non-zero entries in a feas…
Circulation Control for Faster Minimum Cost Flow in Unit-Capacity Graphs
Kyriakos Axiotis, Aleksander Mądry, Adrian Vladu
We present an -time algorithm for solving the minimum cost flow problem in graphs with unit capacity, where is the maximum absolute value of any edge weight…
Fast Modular Subset Sum using Linear Sketching
Kyriakos Axiotis, Arturs Backurs, Christos Tzamos
Given n positive integers, the Modular Subset Sum problem asks if a subset adds up to a given target t modulo a given integer m. This is a natural generalization of the Subset Sum…
Capacitated Dynamic Programming: Faster Knapsack and Graph Algorithms
Kyriakos Axiotis, Christos Tzamos
One of the most fundamental problems in Computer Science is the Knapsack problem. Given a set of n items with different weights and values, it asks to pick the most valuable subset…
On the Size and the Approximability of Minimum Temporally Connected Subgraphs
Kyriakos Axiotis, Dimitris Fotakis
We consider temporal graphs with discrete time labels and investigate the size and the approximability of minimum temporally connected spanning subgraphs. We present a family of mi…