44 citations · 145 across the 18 of their papers we have counts for
19 papers
Restricted Generative Projection for One-Class Classification and Anomaly Detection
Feng Xiao, Ruoyu Sun, Jicong Fan
We present a simple framework for one-class classification and anomaly detection. The core idea is to learn a mapping to transform the unknown distribution of training (normal) dat…
A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programming
Qingyu Han, Linxin Yang, Qian Chen +5
Mixed-integer linear programming (MILP) is widely employed for modeling combinatorial optimization problems. In practice, similar MILP instances with only coefficient variations ar…
Balanced Training for Sparse GANs
Yite Wang, Jing Wu, Naira Hovakimyan +1
Over the past few years, there has been growing interest in developing larger and deeper neural networks, including deep generative models like generative adversarial networks (GAN…
DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data
Tiantian Fang, Ruoyu Sun, Alex Schwing
Generative adversarial nets (GANs) have been remarkably successful at learning to sample from distributions specified by a given dataset, particularly if the given dataset is reaso…
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
Haoxiang Wang, Yite Wang, Ruoyu Sun +1
Model-agnostic meta-learning (MAML) and its variants have become popular approaches for few-shot learning. However, due to the non-convexity of deep neural nets (DNNs) and the bi-l…
Portfolio analysis with mean-CVaR and mean-CVaR-skewness criteria based on mean-variance mixture models
Nuerxiati Abudurexiti, Kai He, Dongdong Hu +3
The paper Zhao et al. (2015) shows that mean-CVaR-skewness portfolio optimization problems based on asymetric Laplace (AL) distributions can be transformed into quadratic optimizat…
Does Momentum Change the Implicit Regularization on Separable Data?
Bohan Wang, Qi Meng, Huishuai Zhang +4
The momentum acceleration technique is widely adopted in many optimization algorithms. However, there is no theoretical answer on how the momentum affects the generalization perfor…
On a Faster -Linear Convergence Rate of the Barzilai-Borwein Method
Dawei Li, Ruoyu Sun
The Barzilai-Borwein (BB) method has demonstrated great empirical success in nonlinear optimization. However, the convergence speed of BB method is not well understood, as the know…
Towards a Better Global Loss Landscape of GANs
Ruoyu Sun, Tiantian Fang, Alex Schwing
Understanding of GAN training is still very limited. One major challenge is its non-convex-non-concave min-max objective, which may lead to sub-optimal local minima. In this work,…
Center-wise Local Image Mixture For Contrastive Representation Learning
Hao Li, Xiaopeng Zhang, Hongkai Xiong
Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the se…
A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems
Jiawei Zhang, Peijun Xiao, Ruoyu Sun +1
Nonconvex-concave min-max problem arises in many machine learning applications including minimizing a pointwise maximum of a set of nonconvex functions and robust adversarial train…
Distilling Object Detectors with Task Adaptive Regularization
Ruoyu Sun, Fuhui Tang, Xiaopeng Zhang +2
Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a…
DEED: A General Quantization Scheme for Communication Efficiency in Bits
Tian Ye, Peijun Xiao, Ruoyu Sun
In distributed optimization, a popular technique to reduce communication is quantization. In this paper, we provide a general analysis framework for inexact gradient descent that i…
Global Convergence and Generalization Bound of Gradient-Based Meta-Learning with Deep Neural Nets
Haoxiang Wang, Ruoyu Sun, Bo Li
Gradient-based meta-learning (GBML) with deep neural nets (DNNs) has become a popular approach for few-shot learning. However, due to the non-convexity of DNNs and the bi-level opt…
Revisiting Landscape Analysis in Deep Neural Networks: Eliminating Decreasing Paths to Infinity
Shiyu Liang, Ruoyu Sun, R. Srikant
Traditional landscape analysis of deep neural networks aims to show that no sub-optimal local minima exist in some appropriate sense. From this, one may be tempted to conclude that…
Sub-Optimal Local Minima Exist for Neural Networks with Almost All Non-Linear Activations
Tian Ding, Dawei Li, Ruoyu Sun
Does over-parameterization eliminate sub-optimal local minima for neural networks? An affirmative answer was given by a classical result in [59] for 1-hidden-layer wide neural netw…
Understanding Limitation of Two Symmetrized Orders by Worst-case Complexity
Peijun Xiao, Zhisheng Xiao, Ruoyu Sun
Update order is one of the major design choices of block decomposition algorithms. There are at least two classes of deterministic update orders: nonsymmetric (e.g. cyclic order) a…
On the Benefit of Width for Neural Networks: Disappearance of Bad Basins
Dawei Li, Tian Ding, Ruoyu Sun
Wide networks are often believed to have a nice optimization landscape, but what rigorous results can we prove? To understand the benefit of width, it is important to identify the…
Globally Optimal Joint Uplink Base Station Association and Beamforming
Wei Liu, Ruoyu Sun, Zhi-Quan Luo +1
The joint base station (BS) association and beamforming problem has been studied extensively in recent years, yet the computational complexity for even the simplest SISO case has n…