← Authors

Michael Mahoney

36 papers · 2013–2025 · 7 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (12) 🌍 Conference Polyglot (7) 🐝 Cross-Pollinator (13) πŸŒ‰ Interdisciplinary Bridge 🌈 Renaissance Researcher (7) πŸ—ΊοΈ Taxonomy Completionist (22) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🏠 Conference Loyalist (22) πŸ† Keyword Champion 🧬 Topic Evolution πŸ”¬ Deep Specialist (10) πŸ”₯ Unstoppable (5) πŸ—ƒοΈ Keyword Collector (61) πŸš€ Conference Pioneer ⚑ Prolific Year (8) ❓ The Questioner πŸ“ˆ Trend Setter πŸ’Ž Century Club (36)

Conferences

ICML (22) AISTATS (7) AAAI (2) EMNLP (2) ACL (1) COLT (1) JMLR (1)

Top co-authors

Zhewei Yao (7) Kurt Keutzer (6) Sheng Shen (5) Amir Gholami (5) Liam Hodgkinson (3) Joseph Gonzalez (2) Jiyan Yang (2) David Gleich (2) Ping Ma (2) Feynman Liang (2)

Research topics

Privacy (1) Statistics (1)

Keywords

neural network optimization (6) stochastic optimization (4) randomized algorithm (4) least square (4) convex optimization (3) leverage score (3) matrix approximation (3) randomized sketching (2) implicit regularization (2) error estimation (2) model compression (2) non-convex optimization (2) stochastic gradient descent (2) numerical linear algebra (2) data augmentation (2) low-rank approximation (2) variational inference (2) combinatorial optimization (2) bootstrap method (2) neural network (2)

Papers

Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic Programming JMLR 2025
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement ACL 2024
NoisyMix: Boosting Model Robustness to Common Corruptions AISTATS 2024
GACT: Activation Compressed Training for Generic Network Architectures ICML 2022
Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers ICML 2022
Neurotoxin: Durable Backdoors in Federated Learning ICML 2022
AutoIP: A United Framework to Integrate Physics into Gaussian Processes ICML 2022
Fat–Tailed Variational Inference with Anisotropic Tail Adaptive Flows ICML 2022
Good Classifiers are Abundant in the Interpolating Regime AISTATS 2021
HAWQ-V3: Dyadic Neural Network Quantization ICML 2021
Sparse sketches with small inversion bias COLT 2021
What’s Hidden in a One-layer Randomly Weighted Transformer? EMNLP 2021
ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning AAAI 2021
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training ICML 2021
Multiplicative Noise and Heavy Tails in Stochastic Optimization ICML 2021
Inefficiency of K-FAC for Large Batch Size Training AAAI 2020
Asymptotic Analysis of Sampling Estimators for Randomized Numerical Linear Algebra Algorithms AISTATS 2020
Statistical guarantees for local graph clustering AISTATS 2020
Bayesian experimental design using regularized determinantal point processes AISTATS 2020
MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding EMNLP 2020
Forecasting Sequential Data Using Consistent Koopman Autoencoders ICML 2020
Error Estimation for Sketched SVD via the Bootstrap ICML 2020
PowerNorm: Rethinking Batch Normalization in Transformers ICML 2020
Traditional and Heavy Tailed Self Regularization in Neural Network Models ICML 2019
FLAG n’ FLARE: Fast Linearly-Coupled Adaptive Gradient Methods AISTATS 2018
Error Estimation for Randomized Least-Squares Algorithms via the Bootstrap ICML 2018
Out-of-sample extension of graph adjacency spectral embedding ICML 2018
A Simple and Strongly-Local Flow-Based Method for Cut Improvement ICML 2016
Statistical and Algorithmic Perspectives on Randomized Sketching for Ordinary Least-Squares ICML 2015
Spectral Gap Error Bounds for Improving CUR Matrix Decomposition and the NystrΓΆm Method AISTATS 2015
A Statistical Perspective on Algorithmic Leveraging ICML 2014
Anti-differentiating approximation algorithms:A case study with min-cuts, spectral, and flow ICML 2014
Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels ICML 2014
Robust Regression on MapReduce ICML 2013
Quantile Regression for Large-scale Applications ICML 2013
Revisiting the Nystrom method for improved large-scale machine learning ICML 2013