Search Results for author:
Found 26 papers, 8 papers with code
Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability
The existence of adversarial attacks on machine learning models imperceptible to a human is still quite a mystery from a theoretical perspective.
Benefits of Transformer: In-Context Learning in Linear Regression Tasks with Unstructured Data
In practice, it is observed that transformer-based models can learn concepts in context in the inference stage.
Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective
Pre-training is known to generate universal representations for downstream tasks in large-scale deep learning such as large language models.
Fair Supervised Learning with A Simple Random Sampler of Sensitive Attributes
As the data-driven decision process becomes dominating for industrial applications, fairness-aware machine learning arouses great attention in various areas.
Personalized Federated X -armed Bandit
In this work, we study the personalized federated $\mathcal{X}$-armed bandit problem, where the heterogeneous local objectives of the clients are optimized simultaneously in the federated learning paradigm.
Enhancing Low-Precision Sampling via Stochastic Gradient Hamiltonian Monte Carlo
This paper investigates low-precision sampling via Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) with low-precision and full-precision gradient accumulators for both strongly log-concave and non-log-concave distributions.
On Neural Network approximation of ideal adversarial attack and convergence of adversarial training
Then we obtain an approximation result of such functions by a neural network.
A New Paradigm for Generative Adversarial Networks based on Randomized Decision Rules
In the new formulation, the discriminator converges to a fixed point while the generator converges to a distribution at the Nash equilibrium.
Matrix Completion from General Deterministic Sampling Patterns
Most of the existing works on provable guarantees for low-rank matrix completion algorithms rely on some unrealistic assumptions such that matrix entries are sampled randomly or the sampling pattern has a specific structure.
PyXAB -- A Python Library for $\mathcal{X}$-Armed Bandit and Online Blackbox Optimization Algorithms
We introduce a Python open-source library for $\mathcal{X}$-armed bandit and online blackbox optimization named PyXAB.
Support Recovery in Sparse PCA with Non-Random Missing Data
We analyze a practical algorithm for sparse PCA on incomplete and noisy data under a general non-random sampling scheme.
Federated X-Armed Bandit
This work establishes the first framework of federated $\mathcal{X}$-armed bandit, where different clients face heterogeneous local objective functions defined on the same domain and are required to collaboratively figure out the global optimum.
Support Recovery in Sparse PCA with Incomplete Data
We study a practical algorithm for sparse principal component analysis (PCA) of incomplete and noisy data.
Benefit of Interpolation in Nearest Neighbor Algorithms
In some studies \citep[e. g.,][]{zhang2016understanding} of deep learning, it is observed that over-parametrized deep neural networks achieve a small testing error even when the training error is almost zero.
Unlabeled Data Help: Minimax Analysis and Adversarial Robustness
The recent proposed self-supervised learning (SSL) approaches successfully demonstrate the great potential of supplementing learning algorithms with additional unlabeled data.
On the Algorithmic Stability of Adversarial Training
In contrast, this paper studies the algorithmic stability of a generic adversarial training algorithm, which can further help to establish an upper bound for generalization error.
Optimum-statistical Collaboration Towards General and Efficient Black-box Optimization
In this paper, we make the key delineation on the roles of resolution and statistical uncertainty in hierarchical bandits-based black-box optimization algorithms, guiding a more general analysis and a more efficient algorithm design.
Consistent Sparse Deep Learning: Theory and Computation
Deep learning has been the engine powering many successes of data science.
Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee
Sparse deep learning aims to address the challenge of huge storage consumption by deep neural networks, and to recover the sparse structure of target functions.
Nearly Optimal Variational Inference for High Dimensional Regression with Shrinkage Priors
We propose a variational Bayesian (VB) procedure for high-dimensional linear model inferences with heavy tail shrinkage priors, such as student-t prior.
Stochastic Gradient Langevin Dynamics Algorithms with Adaptive Drifts
Bayesian deep learning offers a principled way to address many issues concerning safety of artificial intelligence (AI), such as model uncertainty, model interpretability, and prediction bias.
On the Generalization Properties of Adversarial Training
Modern machine learning and deep learning models are shown to be vulnerable when testing data are slightly perturbed.
Predictive Power of Nearest Neighbors Algorithm under Random Perturbation
We consider a data corruption scenario in the classical $k$ Nearest Neighbors ($k$-NN) algorithm, that is, the testing data are randomly perturbed.
Extended Stochastic Gradient MCMC for Large-Scale Bayesian Variable Selection
Stochastic gradient Markov chain Monte Carlo (MCMC) algorithms have received much attention in Bayesian computing for big data problems, but they are only applicable to a small class of problems for which the parameter space has a fixed dimension and the log-posterior density is differentiable with respect to the parameters.
Benefit of Interpolation in Nearest Neighbor Algorithms
The over-parameterized models attract much attention in the era of data science and deep learning.
Statistical Optimality of Interpolated Nearest Neighbor Algorithms
In the era of deep learning, understanding over-fitting phenomenon becomes increasingly important.
