research
∙
08/30/2023
Surrogate-based Autotuning for Randomized Sketching Algorithms in Regression Problems
Algorithms from Randomized Numerical Linear Algebra (RandNLA) are known ...
share
research
∙
07/15/2023
The Interpolating Information Criterion for Overparameterized Models
The problem of model selection is considered for the setting of interpol...
research
∙
07/07/2023
GEANN: Scalable Graph Augmentations for Multi-Horizon Time Series Forecasting
Encoder-decoder deep neural networks have been increasingly studied for ...
research
∙
06/15/2023
A Heavy-Tailed Algebra for Probabilistic Programming
Despite the successes of probabilistic models based on passing noise thr...
research
∙
06/13/2023
SqueezeLLM: Dense-and-Sparse Quantization
Generative Large Language Models (LLMs) have demonstrated remarkable res...
research
∙
05/28/2023
A Three-regime Model of Network Pruning
Recent work has highlighted the complex influence training hyperparamete...
research
∙
05/28/2023
Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
We consider solving equality-constrained nonlinear, nonconvex optimizati...
research
∙
05/21/2023
When are ensembles really effective?
Ensembling has a long history in statistical data analysis, with many im...
research
∙
02/27/2023
Full Stack Optimization of Transformer Inference: a Survey
Recent advances in state-of-the-art DNN architecture design have been mo...
research
∙
02/21/2023
Learning Physical Models that Can Respect Conservation Laws
Recent work in scientific machine learning (SciML) has focused on incorp...
research
∙
02/15/2023
Big Little Transformer Decoder
The recent emergence of Large Language Models based on the Transformer a...
research
∙
11/29/2022
Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems
We propose a trust-region stochastic sequential quadratic programming al...
research
∙
10/14/2022
Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes
The quality of many modern machine learning models improves as model com...
research
∙
10/02/2022
Gradient Gating for Deep Multi-Rate Learning on Graphs
We present Gradient Gating (G^2), a novel framework for improving the pe...
research
∙
07/08/2022
Adaptive Self-supervision Algorithms for Physics-informed Neural Networks
Physics-informed neural networks (PINNs) incorporate physical knowledge ...
research
∙
06/12/2022
Neurotoxin: Durable Backdoors in Federated Learning
Due to their decentralized nature, federated learning (FL) systems have ...
research
∙
06/02/2022
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
The recently proposed Conformer model has become the de facto backbone m...
research
∙
05/27/2022
Asymptotic Convergence Rate and Statistical Inference for Stochastic Sequential Quadratic Programming
We apply a stochastic sequential quadratic programming (StoSQP) algorith...
research
∙
05/16/2022
Fat-Tailed Variational Inference with Anisotropic Tail Adaptive Flows
While fat-tailed densities commonly arise as posterior and marginal dist...
research
∙
05/14/2022
The Sky Above The Clouds
Technology ecosystems often undergo significant transformations as they ...
research
∙
04/20/2022
Hessian Averaging in Stochastic Newton Methods Achieves Superlinear Convergence
We consider minimizing a smooth and strongly convex objective function u...
research
∙
02/28/2022
Fast Feature Selection with Fairness Constraints
We study the fundamental problem of selecting optimal features for model...
research
∙
02/06/2022
Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data
The search for effective and robust generalization metrics has been the ...
research
∙
11/27/2021
Learning from learning machines: a new generation of AI technology to meet the needs of science
We outline emerging opportunities and challenges to enhance the utility ...
research
∙
09/11/2021
Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information
We present a novel adaptive optimization algorithm for large-scale machi...
research
∙
09/08/2021
What's Hidden in a One-layer Randomly Weighted Transformer?
We demonstrate that, hidden within one-layer randomly weighted neural ne...
research
∙
09/02/2021
Characterizing possible failure modes in physics-informed neural networks
Recent work in scientific machine learning has developed so-called physi...
research
∙
08/02/2021
Generalization Properties of Stochastic Optimizers via Trajectory Analysis
Despite the ubiquitous use of stochastic optimization algorithms in mach...
research
∙
07/23/2021
Taxonomizing local versus global structure in neural network loss landscapes
Viewing neural network models in terms of their loss landscapes has a lo...
research
∙
07/15/2021
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update
In second-order optimization, a potential bottleneck can be computing th...
research
∙
06/01/2021
Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metrics
To understand better the causes of good generalization performance in st...
research
∙
05/30/2021
MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models
Pruning is an effective method to reduce the memory footprint and comput...
research
∙
04/29/2021
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
The increasing size of neural network models has been critical for impro...
research
∙
03/31/2021
Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition
End-to-end neural network models achieve improved performance on various...
research
∙
03/25/2021
A Survey of Quantization Methods for Efficient Neural Network Inference
As soon as abstract mathematical computations were adapted to computatio...
research
∙
03/02/2021
Hessian Eigenspectra of More Realistic Nonlinear Models
Given an optimization problem, the Hessian matrix and its eigenspectrum ...
research
∙
01/22/2021
Hessian-Aware Pruning and Optimal Neural Implant
Pruning is an effective method to reduce the memory footprint and FLOPs ...
research
∙
01/05/2021
I-BERT: Integer-only BERT Quantization
Transformer based models, like BERT and RoBERTa, have achieved state-of-...
research
∙
11/21/2020
Sparse sketches with small inversion bias
For a tall n× d matrix A and a random m× n sketching matrix S, the sketc...
research
∙
11/20/2020
HAWQV3: Dyadic Neural Network Quantization
Quantization is one of the key techniques used to make Neural Networks (...
research
∙
10/27/2020
A Statistical Framework for Low-bitwidth Training of Deep Neural Networks
Fully quantized training (FQT), which uses low-bitwidth hardware by quan...
research
∙
10/18/2020
Fast Distributed Training of Deep Neural Networks: Dynamic Communication Thresholding for Model and Data Parallelism
Data Parallelism (DP) and Model Parallelism (MP) are two common paradigm...
research
∙
10/12/2020
MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding
Phrase localization is a task that studies the mapping from textual phra...
research
∙
10/03/2020
Sparse Quantized Spectral Clustering
Given a large data matrix, sparsifying, quantizing, and/or performing ot...
research
∙
08/26/2020
Benchmarking Semi-supervised Federated Learning
Federated learning promises to use the computational power of edge devic...
research
∙
07/09/2020
Boundary thickness and robustness in learning models
Robustness of machine learning models to various adversarial and non-adv...
research
∙
07/02/2020
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization
In distributed second order optimization, a standard strategy is to aver...
research
∙
06/22/2020
Good linear classifiers are abundant in the interpolating regime
Within the machine learning community, the widely-used uniform convergen...
research
∙
06/18/2020
Precise expressions for random projections: Low-rank approximation and randomized Newton
It is often desirable to reduce the dimensionality of a large dataset by...
research
∙
06/11/2020
