AK
Anastasios Kyrillidis
cs.LGmath.OCstat.MLcs.ITmath.ITcs.AIcs.DScs.NAmath.NAquant-ph
On Valency
published · living versionsW_u7fa5rax·v1 · currentpublished
MLSys: The New Frontier of Machine Learning Systems
with Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen +64
1 version
Preprints & journals
103 papers in the corpus · 2012–2026Identity-Paired Progressive Depth Training: When Trainability Persists Beyond Expressibility2607.16800v2 · Athanasios Hadjidimoulas, Tirthak Patel, Anastasios Kyrillidis2026 · 0 citationsarXiv
Provable Deterministic Leverage Score Sampling1404.1530v3 · Dimitris Papailiopoulos, Anastasios Kyrillidis, Christos Boutsidis2014 · 68 citationsarXiv
Dropping Convexity for Faster Semi-definite Optimization1509.03917v3 · Srinadh Bhojanapalli, Anastasios Kyrillidis, Sujay Sanghavi2015 · 47 citationsarXiv
Algorithms for Learning Sparse Additive Models with Interactions in High Dimensions1605.00609v3 · Hemant Tyagi, Anastasios Kyrillidis, Bernd Gartner et al.2016 · 0 citationsarXiv
Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems1606.01316v3 · Dohyung Park, Anastasios Kyrillidis, Srinadh Bhojanapalli et al.2016 · 21 citationsarXiv
Finding Low-Rank Solutions via Non-Convex Matrix Factorization, Efficiently and Provably1606.03168v3 · Dohyung Park, Anastasios Kyrillidis, Constantine Caramanis et al.2016 · 60 citationsarXiv
Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach1609.03240v2 · Dohyung Park, Anastasios Kyrillidis, Constantine Caramanis et al.2016 · 49 citationsarXiv
IHT dies hard: Provable accelerated Iterative Hard Thresholding1712.09379v2 · Rajiv Khanna, Anastasios Kyrillidis2017 · 21 citationsarXiv
Simple and practical algorithms for $\ell_p$-norm low-rank approximation1805.09464v1 · Anastasios Kyrillidis2018 · 4 citationsarXiv
Matrix Recipes for Hard Thresholding Methods1203.4481v2 · Anastasios Kyrillidis, Volkan Cevher2012 · 82 citationsarXiv
Randomized Low-Memory Singular Value Projection1303.0167v3 · Stephen Becker, Volkan Cevher, Anastasios Kyrillidis2013 · 12 citationsarXiv
One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer2605.17811v1 · Jucheng Shen, Barbara Su, Anastasios Kyrillidis2026 · 0 citationsarXiv
Convergence Analysis of Two-Layer Neural Networks under Gaussian Input Masking2602.17423v1 · Afroditi Kolomvaki, Fangshuo Liao, Evan Dramko et al.2026 · 0 citationsarXiv
GHOST: Unmasking Phantom States in Mamba2 via Grouped Hidden-state Output-aware Selection & Truncation2602.11408v1 · Michael Menezes, Anastasios Kyrillidis2026 · 0 citationsarXiv
On The Finetuning of MLIPs Through the Lens of Iterated Maps With BPTT2512.01067v2 · Evan Dramko, Yizhi Zhu, Aleksandar Krivokapic et al.2025 · 0 citationsarXiv
Completion of partial structures using Patterson maps with the CrysFormer machine-learning model.41284364 · Pan, Tom, Dramko, Evan, Miller, Mitchell D et al.2025 · 1 citationActa crystallographica. Section D, Structural biology. 2025;81(Pt 12):668-677
A Catalyst Framework for the Quantum Linear System Problem via the Proximal Point Algorithm2406.13879v2 · Junhyung Lyle Kim, Nai-Hui Chia, Anastasios Kyrillidis2024 · 0 citationsarXiv
Completion of partial structures using Patterson maps with the CrysFormer machine learning model2511.10440v1 · Tom Pan, Evan Dramko, Mitchell D. Miller et al.2025 · 1 citationarXiv
TwIST: Rigging the Lottery in Transformers with Independent Subnetwork Training2511.03983v1 · Michael Menezes, Barbara Su, Xinze Feng et al.2025 · 0 citationsarXiv
Three Birds with One Stone: Improving Performance, Convergence, and System Throughput with Nest2510.09578v1 · Yuqian Huo, David Quiroga, Anastasios Kyrillidis et al.2025 · 0 citationsarXiv
Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings2306.08586v3 · Yehya Farhat, Hamza ElMokhtar Shili, Fangshuo Liao et al.2023 · 3 citationsarXiv
Thinking Out of the Box: Hybrid SAT Solving by Unconstrained Continuous Optimization2506.00674v1 · Zhiwei Zhang, Samy Wu Fung, Anastasios Kyrillidis et al.2025 · 0 citationsarXiv
Exploring How LLMs Capture and Represent Domain-Specific Knowledge2504.16871v2 · Mirian Hipolito Garcia, Camille Couturier, Daniel Madrigal Diaz et al.2025 · 0 citationsarXiv
RecCrysFormer: Refined Protein Structural Prediction from 3D Patterson Maps via Recycling Training Runs2503.00143v1 · Tom Pan, Evan Dramko, Mitchell D. Miller et al.2025 · 0 citationsarXiv
Provable Model-Parallel Distributed Principal Component Analysis with Parallel Deflation2502.17615v1 · Fangshuo Liao, Wenyi Su, Anastasios Kyrillidis2025 · 0 citationsarXiv
Grover-QAOA for 3-SAT: Quadratic Speedup, Fair-Sampling, and Parameter Clustering2402.02585v1 · Zewen Zhang, Roger Paredes, Bhuvanesh Sundar et al.2024 · 13 citationsQuantum Sci. Technol. 10 015022 (2025)
Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation2310.02842v3 · Chen Dun, Mirian Hipolito Garcia, Guoqing Zheng et al.2023 · 3 citationsarXiv
Using non-convex optimization in quantum process tomography: Factored gradient descent is tough to beat2312.01311v1 · David A. Quiroga, Anastasios Kyrillidis2023 · 2 citations2023 IEEE International Conference on Rebooting Computing (ICRC) 118-127
On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis2310.04283v2 · Fangshuo Liao, Junhyung Lyle Kim, Cruz Barnum et al.2023 · 0 citationsarXiv
Adaptive Federated Learning with Auto-Tuned Clients2306.11201v3 · Junhyung Lyle Kim, Mohammad Taha Toghani, C'esar A. Uribe et al.2023 · 3 citationsarXiv
Better Schedules for Low Precision Training of Deep Neural Networks2403.02243v1 · Cameron R. Wolfe, Anastasios Kyrillidis2024 · 3 citationsMachine Learning (2024): 1-19
When is Momentum Extragradient Optimal? A Polynomial-Based Analysis2211.04659v3 · Junhyung Lyle Kim, Gauthier Gidel, Anastasios Kyrillidis et al.2022 · 0 citationsarXiv
Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks2306.08109v2 · Fangshuo Liao, Anastasios Kyrillidis2023 · 0 citationsarXiv
CrysFormer: Protein Structure Prediction via 3d Patterson Maps and Partial Structure Attention2310.03899v1 · Chen Dun, Qiutai Pan, Shikai Jin et al.2023 · 0 citationsarXiv
Stochastic Implicit Neural Signed Distance Functions for Safe Motion Planning under Sensing Uncertainty2309.16862v1 · Carlos Quintero-Pena, Wil Thomason, Zachary Kingston et al.2023 · 9 citationsarXiv
Federated Learning Over Images: Vertical Decompositions and Pre-Trained Backbones Are Difficult to Beat2309.03237v1 · Erdong Hu, Yuxin Tang, Anastasios Kyrillidis et al.2023 · 13 citationsarXiv
Fast FixMatch: Faster Semi-Supervised Learning with Curriculum Batch Size2309.03469v1 · John Chen, Chen Dun, Anastasios Kyrillidis2023 · 5 citationsarXiv
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time2305.17118v2 · Zichang Liu, Aditya Desai, Fangshuo Liao et al.2023 · 33 citationsarXiv
How much pre-training is enough to discover a good subnetwork?2108.00259v3 · Cameron R. Wolfe, Fangshuo Liao, Qihan Wang et al.2021 · 1 citationarXiv
A deep learning solution for crystallographic structure determination.37409806 · Pan, Tom, Jin, Shikai, Miller, Mitchell D et al.2023 · 19 citationsIUCrJ. 2023;10(Pt 4):487-496
Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum2111.06171v5 · Junhyung Lyle Kim, Panos Toulis, Anastasios Kyrillidis2021 · 0 citationsarXiv
DPMS: An ADD-Based Symbolic Approach for Generalized MaxSAT Solving2205.03747v2 · Anastasios Kyrillidis, Moshe Y. Vardi, Zhiwei Zhang2022 · 1 citationarXiv
Momentum-inspired Low-Rank Coordinate Descent for Diagonally Constrained SDPs2106.08775v2 · Junhyung Lyle Kim, JA Lara Benitez, Mohammad Taha Toghani et al.2021 · 0 citationsarXiv
Cold Start Streaming Learning for Deep Networks2211.04624v1 · Cameron R. Wolfe, Anastasios Kyrillidis2022 · 2 citationsarXiv
Strong Lottery Ticket Hypothesis with $\varepsilon$--perturbation2210.16589v1 · Zheyang Xiong, Fangshuo Liao, Anastasios Kyrillidis2022 · 0 citationsarXiv
Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout2210.16105v1 · Chen Dun, Mirian Hipolito, Chris Jermaine et al.2022 · 7 citationsarXiv
LOFT: Finding Lottery Tickets through Filter-wise Training2210.16169v1 · Qihan Wang, Chen Dun, Fangshuo Liao et al.2022 · 1 citationarXiv
On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons2112.02668v2 · Fangshuo Liao, Anastasios Kyrillidis2021 · 2 citationsarXiv
No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds2203.02502v2 · Ahmed Imtiaz Humayun, Randall Balestriero, Anastasios Kyrillidis et al.2022 · 1 citationarXiv
Local Stochastic Factored Gradient Descent for Distributed Quantum State Tomography2203.11579v2 · Junhyung Lyle Kim, Mohammad Taha Toghani, C'esar A. Uribe et al.2022 · 1 citationarXiv
Career total: 168 works. 103 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.