
NeurIPS 2020 Competition: Predicting Generalization in Deep Learning
Understanding generalization in deep learning is arguably one of the mos...
read it

When Do Curricula Work?
Inspired by human learning, researchers have proposed ordering examples ...
read it

Understanding the Failure Modes of OutofDistribution Generalization
Empirical studies suggest that machine learning models often rely on fea...
read it

Are wider nets better given the same number of parameters?
Empirical studies demonstrate that the performance of neural networks im...
read it

The Deep Bootstrap: Good Online Learners are Good Offline Generalizers
We propose a new framework for reasoning about generalization in deep le...
read it

SharpnessAware Minimization for Efficiently Improving Generalization
In today's heavily overparameterized models, the value of the training l...
read it

Extreme Memorization via Scale of Initialization
We construct an experimental setup in which changing the scale of initia...
read it

What is being transferred in transfer learning?
One desired capability for machines is the ability to transfer their kno...
read it

Towards Learning Convolutions from Scratch
Convolution is one of the most essential components of architectures use...
read it

Observational Overfitting in Reinforcement Learning
A major component of overfitting in modelfree reinforcement learning (R...
read it

Fantastic Generalization Measures and Where to Find Them
Generalization of deep networks has been of great interest in recent yea...
read it

The intriguing role of module criticality in the generalization of deep networks
We study the phenomenon that some modules of deep neural networks (DNNs)...
read it

Towards Understanding the Role of OverParametrization in Generalization of Neural Networks
Despite existing work on ensuring generalization of neural networks in t...
read it

Stronger generalization bounds for deep nets via a compression approach
Deep nets generalize well despite having more parameters than the number...
read it

Implicit Regularization in Matrix Factorization
We study implicit regularization when optimizing an underdetermined quad...
read it

Stabilizing GAN Training with Multiple Random Projections
Training generative adversarial networks is unstable in highdimensions ...
read it

Corralling a Band of Bandit Algorithms
We study the problem of combining multiple bandit algorithms (that is, o...
read it

Global Optimality of Local Search for Low Rank Matrix Recovery
We show that there are no spurious local minima in the nonconvex factor...
read it

PathNormalized Optimization of Recurrent Neural Networks with ReLU Activations
We investigate the parameterspace geometry of recurrent neural networks...
read it

PathSGD: PathNormalized Optimization in Deep Neural Networks
We revisit the choice of SGD for training deep neural networks by recons...
read it

NormBased Capacity Control in Neural Networks
We investigate the capacity, convexity and characterization of a general...
read it

In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
We present experiments demonstrating that some other form of capacity co...
read it

On Symmetric and Asymmetric LSHs for Inner Product Search
We consider the problem of designing locality sensitive hashes (LSH) for...
read it

The Power of Asymmetry in Binary Hashing
When approximating binary similarity using the hamming distance between ...
read it

Sparse Matrix Factorization
We investigate the problem of factorizing a matrix into several sparse m...
read it
Behnam Neyshabur
is this you? claim profile
Research Scholar at Institute for Advanced Study since 2017, PhD Student at Toyota Technological Institute at Chicago (TTIC) from 20112017, Research Intern at MicrosoftNYC 2016, Research Intern at Microsoft Silicon Valley 2013, (PhD), Computer Science at Toyota Technological Institute at Chicago 20112017.