Search Results for author:
Found 14 papers, 1 papers with code
How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers
We prove that such a random NN interpolator typically generalizes well if there exists an underlying narrow ``teacher NN" that agrees with the labels.
Provable Learning of Convolutional Neural Networks with Data Driven Features
Convolutional networks (CNN) are computationally hard to learn.
A Theoretical Analysis of Fine-tuning with Linear Teachers
We further present results on shallow ReLU models, and analyze the dependence of sample complexity there on source and target tasks.
Towards Understanding Learning in Neural Networks with Linear Teachers
Can a neural network minimizing cross-entropy learn linearly separable data?
On Learning Read-once DNFs With Neural Networks
Here we focus on this setting where the functions are learned by a convex neural network and gradient descent.
On the Inductive Bias of a CNN for Distributions with Orthogonal Patterns
In this work, we consider a simplified image classification task where images contain orthogonal patches and are learned with a 3-layer overparameterized convolutional network and stochastic gradient descent (SGD).
An Optimization and Generalization Analysis for Max-Pooling Networks
Max-Pooling operations are a core component of deep learning architectures.
On the Optimality of Trees Generated by ID3
Since its inception in the 1980s, ID3 has become one of the most successful and widely used algorithms for learning decision trees.
ID3 Learns Juntas for Smoothed Product Distributions
In recent years, there are many attempts to understand popular heuristics.
Over-parameterization Improves Generalization in the XOR Detection Problem
Empirical evidence suggests that neural networks with ReLU activations generalize better with over-parameterization.
Low Latency Privacy Preserving Inference
When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity.
Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem
Empirical evidence suggests that neural networks with ReLU activations generalize better with over-parameterization.
SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data
Neural networks exhibit good generalization behavior in the over-parameterized regime, where the number of network parameters exceeds the number of observations.
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
Deep learning models are often successfully trained using gradient descent, despite the worst case hardness of the underlying non-convex optimization problem.
