research
∙
08/28/2023
Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing
We consider the problem of parameter estimation from observations given ...
share
research
∙
05/23/2023
Improved Convergence of Score-Based Diffusion Models via Prediction-Correction
Score-based generative models (SGMs) are powerful tools to sample from c...
research
∙
05/22/2023
Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model
Neural collapse (NC) refers to the surprising structure of the last laye...
research
∙
05/20/2023
Stability, Generalization and Privacy: Precise Analysis for Random and NTK Features
Deep learning models can be vulnerable to recovery attacks, raising priv...
research
∙
03/13/2023
Concentration without Independence via Information Measures
We propose a novel approach to concentration for non-independent random ...
research
∙
02/07/2023
Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise
We study the performance of a Bayesian statistician who estimates a rank...
research
∙
02/03/2023
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels
Machine learning models are vulnerable to adversarial perturbations, and...
research
∙
12/03/2022
Approximate Message Passing for Multi-Layer Estimation in Rotationally Invariant Models
We consider the problem of reconstructing the signal and the hidden vari...
research
∙
11/21/2022
Precise Asymptotics for Spectral Methods in Mixed Generalized Linear Models
In a mixed generalized linear model, the objective is to learn multiple ...
research
∙
11/08/2022
Finite Sample Identification of Wide Shallow Neural Networks with Biases
Artificial neural networks are functions depending on a finite number of...
research
∙
10/13/2022
Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence
The stochastic heavy ball method (SHB), also known as stochastic gradien...
research
∙
10/03/2022
Bayes-optimal limits in structured PCA, and how to reach them
We study the paradigmatic spiked matrix model of principal components an...
research
∙
05/20/2022
Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization
The Neural Tangent Kernel (NTK) has emerged as a powerful tool to provid...
research
∙
05/20/2022
The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation?
We consider the problem of estimating a rank-1 signal corrupted by struc...
research
∙
05/17/2022
Sharp asymptotics on the compression of two-layer neural networks
In this paper, we study the compression of a target two-layer neural net...
research
∙
01/25/2022
Polar Coded Computing: The Role of the Scaling Exponent
We consider the problem of coded distributed computing using polar codes...
research
∙
12/08/2021
Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing
We consider the problem of signal estimation in generalized linear model...
research
∙
11/30/2021
Successive Syndrome-Check Decoding of Polar Codes
A two-part successive syndrome-check decoding of polar codes is proposed...
research
∙
11/03/2021
Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks
Understanding the properties of neural networks trained via stochastic g...
research
∙
09/05/2021
Decoding Reed-Muller Codes with Successive Factor-Graph Permutations
This paper presents a novel successive factor-graph permutation (SFP) sc...
research
∙
06/04/2021
PCA Initialization for Approximate Message Passing in Rotationally Invariant Models
We study the problem of estimating a rank-1 signal in the presence of ro...
research
∙
02/18/2021
On Connectivity of Solutions in Deep Learning: The Role of Over-parameterization and Feature Quality
It has been empirically observed that, in deep neural networks, the solu...
research
∙
12/24/2020
Parallelism versus Latency in Simplified Successive-Cancellation Decoding of Polar Codes
This paper characterizes the latency of the simplified successive-cancel...
research
∙
12/21/2020
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
A recent line of work has analyzed the theoretical properties of deep ne...
research
∙
11/25/2020
Sparse Multi-Decoder Recursive Projection Aggregation for Reed-Muller Codes
Reed-Muller (RM) codes are one of the oldest families of codes. Recently...
research
∙
10/07/2020
Approximate Message Passing with Spectral Initialization for Generalized Linear Models
We consider the problem of estimating a signal from measurements obtaine...
research
∙
08/07/2020
Optimal Combination of Linear and Spectral Estimators for Generalized Linear Models
We study the problem of recovering an unknown signal x given measurement...
research
∙
02/18/2020
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology
A recent line of research has provided convergence guarantees for gradie...
research
∙
12/20/2019
Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks
The optimization of multilayer neural networks typically leads to a solu...
research
∙
09/11/2019
Sublinear Latency for Simplified Successive Cancellation Decoding of Polar Codes
In this work we analyze the latency of the simplified successive cancell...
research
∙
03/21/2019
Rate-Flexible Fast Polar Decoders
Polar codes have gained extensive attention during the past few years an...
research
∙
01/05/2019
Analysis of a Two-Layer Neural Network via Displacement Convexity
Fitting a function by using linear combinations of a large number N of `...
research
∙
07/11/2018
Decoding Reed-Muller and Polar Codes by Successive Factor Graph Permutations
Reed-Muller (RM) and polar codes are a class of capacity-achieving chann...
research
∙
06/28/2018
On the Decoding of Polar Codes on Permuted Factor Graphs
Polar codes are a channel coding scheme for the next generation of wirel...
research
∙
02/20/2018
On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition
We establish connections between the problem of learning a two-layers ne...
research
∙
01/09/2018
A New Coding Paradigm for the Primitive Relay Channel
We present a coding paradigm that provides a new achievable rate for the...
research
∙
08/20/2017