Search Results for author:
Found 10 papers, 1 papers with code
On the best approximation by finite Gaussian mixtures
We consider the problem of approximating a general Gaussian location mixture by finite mixtures.
Two Phases of Scaling Laws for Nearest Neighbor Classifiers
We show that a scaling law can have two phases: in the first phase, the generalization error depends polynomially on the data dimension and decreases fast; whereas in the second phase, the error depends exponentially on the data dimension and decreases slowly.
Federated Learning in the Presence of Adversarial Client Unavailability
Federated learning is a decentralized machine learning framework that enables collaborative model training without revealing raw data.
Global Convergence of Federated Learning for Mixed Regression
This paper studies the problem of model training under Federated Learning when clients exhibit cluster structure.
Deep Active Learning with Noise Stability
We provide theoretical analyses by leveraging the small Gaussian noise theory and demonstrate that our method favors a subset with large and diverse gradients.
Boosting Active Learning via Improving Test Performance
In this work, we explore such an impact by theoretically proving that selecting unlabeled data of higher gradient norm leads to a lower upper-bound of test loss, resulting in better test performance.
A Non-parametric View of FedAvg and FedProx: Beyond Stationary Points
We discover that when the data heterogeneity is moderate, a client with limited local data can benefit from a common model with a large federation gain.
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks
This new representation overcomes the degenerate situation where all the hidden units essentially have only one meaningful hidden unit in each middle layer, and further leads to a simpler representation of DNNs, for which the training objective can be reformulated as a convex optimization problem via suitable re-parameterization.
Optimal estimation of high-dimensional location Gaussian mixtures
This paper studies the optimal rate of estimation in a finite Gaussian location mixture model in high dimensions without separation conditions.
On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective
When the network is sufficiently over-parameterized, these matrices individually approximate {\em an} integral operator which is determined by the feature vector distribution $\rho$ only.
