Search Results for author:
Found 20 papers, 1 papers with code
Better-than-KL PAC-Bayes Bounds
In this paper, we consider the problem of proving concentration inequalities to estimate the mean of the sequence.
Tighter PAC-Bayes Bounds Through Coin-Betting
We consider the problem of estimating the mean of a sequence of random elements $f(X_1, \theta)$ $, \ldots, $ $f(X_n, \theta)$ where $f$ is a fixed scalar function, $S=(X_1, \ldots, X_n)$ are independent random variables, and $\theta$ is a possibly $S$-dependent parameter.
Learning Lipschitz Functions by GD-trained Shallow Overparameterized ReLU Neural Networks
We explore the ability of overparameterized shallow ReLU neural networks to learn Lipschitz, nondifferentiable, bounded functions with additive noise when trained by Gradient Descent (GD).
Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel
We revisit on-average algorithmic stability of GD for training overparameterised shallow neural networks and prove new generalisation and excess risk bounds without the NTK or PL assumptions.
On the Role of Optimization in Double Descent: A Least Squares Study
Empirically it has been observed that the performance of deep neural networks steadily improves as we increase model size, contradicting the classical view on overfitting and generalization.
Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping
We explore the ability of overparameterized shallow neural networks to learn Lipschitz regression functions with and without label noise when trained by Gradient Descent (GD).
A Distribution-Dependent Analysis of Meta-Learning
A key problem in the theory of meta-learning is to understand how the task distributions influence transfer risk, the expected error of a meta-learner on a new task drawn from the unknown task distribution.
PAC-Bayes Analysis Beyond the Usual Bounds
Specifically, we present a basic PAC-Bayes inequality for stochastic kernels, from which one may derive extensions of various known PAC-Bayes bounds as well as novel bounds.
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting
We consider off-policy evaluation in the contextual bandit setting for the purpose of obtaining a robust off-policy selection strategy, where the selection strategy is evaluated based on the value of the chosen policy in a set of proposal (target) policies.
Locally-Adaptive Nonparametric Online Learning
When competing against "simple" locality profiles, our technique delivers regret bounds that are significantly better than those proven using the previous approach.
Efron-Stein PAC-Bayesian Inequalities
We prove semi-empirical concentration inequalities for random variables which are given as possibly nonlinear functions of independent random variables.
Distribution-Dependent Analysis of Gibbs-ERM Principle
This is a well-established notion of effective dimension appearing in several previous works, including the analyses of SGD and ridge regression, but ours is the first work that brings this dimension to the analysis of learning using Gibbs densities.
Efficient Linear Bandits through Matrix Sketching
More precisely, we show that a sketch of size $m$ allows a $\mathcal{O}(md)$ update time for both algorithms, as opposed to $\Omega(d^2)$ required by their non-sketched versions in general (where $d$ is the dimension of context vectors).
Nonparametric Online Regression while Learning the Metric
We study algorithms for online nonparametric regression that learn the directions along which the regression function is smoother.
Data-Dependent Stability of Stochastic Gradient Descent
We establish a data-dependent notion of algorithmic stability for Stochastic Gradient Descent (SGD), and employ it to develop novel generalization bounds.
When Naive Bayes Nearest Neighbors Meet Convolutional Neural Networks
Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbor (NBNN)-based classifiers have lost momentum in the community.
When Naïve Bayes Nearest Neighbours Meet Convolutional Neural Networks
Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbour (NBNN)-based classifiers have lost momentum in the community.
Fast Rates by Transferring from Auxiliary Hypotheses
In this work we consider the learning setting where, in addition to the training set, the learner receives a collection of auxiliary hypotheses originating from other tasks.
Scalable Greedy Algorithms for Transfer Learning
In this paper we consider the binary transfer learning problem, focusing on how to select and combine sources from a large pool to yield a good performance on a target task.
From N to N+1: Multiclass Transfer Incremental Learning
Since the seminal work of Thrun [17], the learning to learn paradigm has been defined as the ability of an agent to improve its performance at each task with experience, with the number of tasks.
