48 citations · 108 across the 26 of their papers we have counts for
26 papers
On Neural Network approximation of ideal adversarial attack and convergence of adversarial training
Rajdeep Haldar, Qifan Song
Adversarial attacks are usually expressed in terms of a gradient-based operation on the input data and model, this results in heavy computations every time an attack is generated.…
A New Paradigm for Generative Adversarial Networks based on Randomized Decision Rules
Sehwan Kim, Qifan Song, Faming Liang
The Generative Adversarial Network (GAN) was recently introduced in the literature as a novel machine learning method for training generative models. It has many applications in st…
Matrix Completion from General Deterministic Sampling Patterns
Hanbyul Lee, Rahul Mazumder, Qifan Song +1
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 th…
PyXAB -- A Python Library for -Armed Bandit and Online Blackbox Optimization Algorithms
Wenjie Li, Haoze Li, Jean Honorio +1
We introduce a Python open-source library for -armed bandit and online blackbox optimization named PyXAB. PyXAB contains the implementations for more than 10 $\mathcal…
Support Recovery in Sparse PCA with Non-Random Missing Data
Hanbyul Lee, Qifan Song, Jean Honorio
We analyze a practical algorithm for sparse PCA on incomplete and noisy data under a general non-random sampling scheme. The algorithm is based on a semidefinite relaxation of the…
Support Recovery in Sparse PCA with Incomplete Data
Hanbyul Lee, Qifan Song, Jean Honorio
We study a practical algorithm for sparse principal component analysis (PCA) of incomplete and noisy data. Our algorithm is based on the semidefinite program (SDP) relaxation of th…
Federated X-Armed Bandit
Wenjie Li, Qifan Song, Jean Honorio +1
This work establishes the first framework of federated -armed bandit, where different clients face heterogeneous local objective functions defined on the same domain a…
Benefit of Interpolation in Nearest Neighbor Algorithms
Yue Xing, Qifan Song, Guang Cheng
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 tra…
Unlabeled Data Help: Minimax Analysis and Adversarial Robustness
Yue Xing, Qifan Song, Guang Cheng
The recent proposed self-supervised learning (SSL) approaches successfully demonstrate the great potential of supplementing learning algorithms with additional unlabeled data. Howe…
Optimum-statistical Collaboration Towards General and Efficient Black-box Optimization
Wenjie Li, Chi-Hua Wang, Guang Cheng +1
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 ge…
A Langevinized Ensemble Kalman Filter for Large-Scale Static and Dynamic Learning
Peiyi Zhang, Qifan Song, Faming Liang
The Ensemble Kalman Filter (EnKF) has achieved great successes in data assimilation in atmospheric and oceanic sciences, but its failure in convergence to the right filtering distr…
Consistent Sparse Deep Learning: Theory and Computation
Yan Sun, Qifan Song, Faming Liang
Deep learning has been the engine powering many successes of data science. However, the deep neural network (DNN), as the basic model of deep learning, is often excessively over-pa…
Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee
Jincheng Bai, Qifan Song, Guang Cheng
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. Although tremendous…
Nearly Optimal Variational Inference for High Dimensional Regression with Shrinkage Priors
Jincheng Bai, Qifan Song, Guang Cheng
We propose a variational Bayesian (VB) procedure for high-dimensional linear model inferences with heavy tail shrinkage priors, such as student-t prior. Theoretically, we establish…
Stochastic Gradient Langevin Dynamics Algorithms with Adaptive Drifts
Sehwan Kim, Qifan Song, Faming Liang
Bayesian deep learning offers a principled way to address many issues concerning safety of artificial intelligence (AI), such as model uncertainty,model interpretability, and predi…
On the Generalization Properties of Adversarial Training
Yue Xing, Qifan Song, Guang Cheng
Modern machine learning and deep learning models are shown to be vulnerable when testing data are slightly perturbed. Existing theoretical studies of adversarial training algorithm…
Bayesian Shrinkage towards Sharp Minimaxity
Qifan Song
Shrinkage prior are becoming more and more popular in Bayesian modeling for high dimensional sparse problems due to its computational efficiency. Recent works show that a polynomia…
Predictive Power of Nearest Neighbors Algorithm under Random Perturbation
Yue Xing, Qifan Song, Guang Cheng
We consider a data corruption scenario in the classical Nearest Neighbors (-NN) algorithm, that is, the testing data are randomly perturbed. Under such a scenario, the impac…
Extended Stochastic Gradient MCMC for Large-Scale Bayesian Variable Selection
Qifan Song, Yan Sun, Mao Ye +1
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 cla…
Adaptive Variational Bayesian Inference for Sparse Deep Neural Network
Jincheng Bai, Qifan Song, Guang Cheng
In this work, we focus on variational Bayesian inference on the sparse Deep Neural Network (DNN) modeled under a class of spike-and-slab priors. Given a pre-specified sparse DNN st…
Benefit of Interpolation in Nearest Neighbor Algorithms
Yue Xing, Qifan Song, Guang Cheng
The over-parameterized models attract much attention in the era of data science and deep learning. It is empirically observed that although these models, e.g. deep neural networks,…
Bayesian Fusion Estimation via t-Shrinkage
Qifan Song, Guang Cheng
Shrinkage prior has gained great successes in many data analysis, however, its applications mostly focus on the Bayesian modeling of sparse parameters. In this work, we will apply…
Optimal False Discovery Control of Minimax Estimator
Qifan Song, Guang Cheng
Two major research tasks lie at the heart of high dimensional data analysis: accurate parameter estimation and correct support recovery. The existing literature mostly aims for eit…
Statistical Optimality of Interpolated Nearest Neighbor Algorithms
Yue Xing, Qifan Song, Guang Cheng
In the era of deep learning, understanding over-fitting phenomenon becomes increasingly important. It is observed that carefully designed deep neural networks achieve small testing…