Search results
Mar 22, 2024 · Michael Mahoney. I am in the Department of Statistics at UC Berkeley; I am also at the International Computer Science Institute (ICSI, where I am Vice President and Director of the Big Data Group ) and the Lawrence Berkeley National Laboratory (LBNL, where I am the Group Lead for the Machine Learning and Analytics Group ); I am also in the ...
2323. 2009. Empirical comparison of algorithms for network community detection. J Leskovec, KJ Lang, M Mahoney. Proceedings of the 19th international conference on World wide web, 631-640. , 2010. 1266. 2010. Statistical properties of community structure in large social and information networks.
- 2024
- 2023
- 2022
- 2021
- 2020
- 2019
- 2018
- 2017
- 2016
- 2015
AI and Memory Wall,Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs,Chronos: Learning the Language of Time Series,Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning,Multi-scale Local Network Structure Critically Impacts Epidemic Spread and Interventions,An LLM Compiler for Parallel Function Calling,Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training,DMLR: Data-centric Machine Learning Research -- Past, Present and Future,Gated Recurrent Neural Networks with Weighted Time-Delay Feedback,Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems,Randomized Numerical Linear Algebra: A Perspective on the Field With an Eye to Software,Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes,Learning from learning machines: a new generation of AI technology to meet the needs of science,Long Expressive Memory for Sequence Modeling,Noisy Feature Mixup,Inexact Newton-CG Algorithms With Complexity Guarantees,Sparse sketches with small inversion bias,HAWQV3: Dyadic Neural Network Quantization,A Statistical Framework for Low-bitwidth Training of Deep Neural Networks,Training Recommender Systems at Scale: Communication-Efficient Model and Data Parallelism,PyHessian: Neural Networks Through the Lens of the Hessian,Exact expressions for double descent and implicit regularization via surrogate random design,LSAR: Efficient Leverage Score Sampling Algorithm for the Analysis of Big Time Series Data,HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks,Trust Region Based Adversarial Attack on Neural Networks,Parameter Re-Initialization through Cyclical Batch Size Schedules,On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent,The Mathematics of Data,Lectures on Randomized Numerical Linear Algebra,Avoiding Synchronization in First-Order Methods for Sparse Convex Optimization,Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior,(click herefor a blog about this paper)LASAGNE: Locality And Structure Aware Graph Node Embedding,Avoiding communication in primal and dual block coordinate descent methods,Feature-distributed sparse regression: a screen-and-clean approach,Multi-label learning with semantic embeddings,Mapping the Similarities of Spectra: Global and Locally-biased Approaches to SDSS Galaxy Data,Faster Parallel Solver for Positive Linear Programs via Dynamically-Bucketed Selective Coordinate Descent,A Local Perspective on Community Structure in Multilayer Networks,Optimal Subsampling Approaches for Large Sample Linear Regression,Unified Acceleration Method for Packing and Covering Problems via Diameter Reduction,Research Areas. Statistical Computing. Applications in the Physical and Environmental Sciences. Applications in the Social Sciences. High Dimensional Data Analysis. Artificial Intelligence/Machine Learning.
Michael Mahoney - Presentations. Talks and Presentations. Recent tutorial presentations : Recent and Upcoming Developments in Randomized Numerical Linear Algebra for ML ( December 2023, Tutorial at 2023 NeurIPS ) ( pdf )
Michael W. Mahoney. Dynamical systems that evolve continuously over time are ubiquitous throughout science and engineering. Machine learning (ML) provides data-driven approaches to model and...
Associate Professor, Statistics, UC Berkeley. Michael Mahoney works on algorithmic and statistical aspects of modern large-scale data analysis. Much of his recent research has focused on large-scale machine learning including randomized matrix algorithms and randomized numerical linear algebra; geometric network analysis tools for structure ...
![DVIDS - Images - Michael Mahoney [Image 9 of 17]](https://images.search.yahoo.com/search/images?p=Michael+Mahoney&ei=UTF-8&xargs=0&norw=1&_tsrc=apple&age=1d&th=98.3&tw=78.7&imgurl=https%3A%2F%2Fd1ldvf68ux039x.cloudfront.net%2Fthumbs%2Fphotos%2F1708%2F3630639%2F1000w_q95.jpg&rurl=https%3A%2F%2Fwww.dvidshub.net%2Fimage%2F3630639%2Fmichael-mahoney&size=326KB&name=DVIDS+-+Images+-+Michael+Mahoney+%5BImage+9+of+17%5D&oid=1&h=1250&w=1000&turl=https%3A%2F%2Ftse1.mm.bing.net%2Fth%3Fid%3DOIP.vfEEI_bBuA0oeYAx6JhgpgHaJQ%26pid%3DApi%26rs%3D1%26c%3D1%26qlt%3D95%26w%3D78%26h%3D98&tt=DVIDS+-+Images+-+Michael+Mahoney+%5BImage+9+of+17%5D&sigr=YKCYO7myaU8S&sigit=6cusU6sHHXeP&sigi=qUIEMrMFycJo&sign=BfdYmeNGg6V8&sigt=BfdYmeNGg6V8 "DVIDS - Images - Michael Mahoney [Image 9 of 17]")
