Search Results for author: Haoran Sun

Found 26 papers, 4 papers with code

Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking

no code implementations ICML 2020 Haoran Sun, Songtao Lu, Mingyi Hong

Similarly, for online problems, the proposed method achieves an $\mathcal{O}(m \epsilon^{-3/2})$ sample complexity and an $\mathcal{O}(\epsilon^{-1})$ communication complexity, while the best existing bounds are $\mathcal{O}(m\epsilon^{-2})$ and $\mathcal{O}(\epsilon^{-2})$.

Stochastic Optimization

Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets

no code implementations13 Jun 2023 Yurong Chen, Qian Wang, Zhijian Duan, Haoran Sun, Zhaohua Chen, Xiang Yan, Xiaotie Deng

To the best of our knowledge, we are the first to consider bidder coordination in online repeated auctions with constraints.

A Scalable Neural Network for DSIC Affine Maximizer Auction Design

no code implementations20 May 2023 Zhijian Duan, Haoran Sun, Yurong Chen, Xiaotie Deng

AMenuNet is always DSIC and individually rational (IR) due to the properties of AMAs, and it enhances scalability by generating candidate allocations through a neural network.

Two-Bit RIS-Aided Communications at 3.5GHz: Some Insights from the Measurement Results Under Multiple Practical Scenes

no code implementations19 May 2023 Shun Zhang, Haoran Sun, Runze Yu, Hongshenyuan Cui, Jian Ren, Feifei Gao, Shi Jin, Hongxiang Xie, Hao Wang

In particular, we adopt a self-developed broadband intelligent communication system 40MHz-Net (BICT-40N) terminal in order to fully acquire the channel information.

Intelligent Communication Quantization

Fine-grained Cross-modal Fusion based Refinement for Text-to-Image Synthesis

1 code implementation17 Feb 2023 Haoran Sun, Yang Wang, Haipeng Liu, Biao Qian

The proposed FF-Block integrates an attention block and several convolution layers to effectively fuse the fine-grained word-context features into the corresponding visual features, in which the text information is fully used to refine the initial image with more details.

Image Generation

Score-based Continuous-time Discrete Diffusion Models

no code implementations30 Nov 2022 Haoran Sun, Lijun Yu, Bo Dai, Dale Schuurmans, Hanjun Dai

Score-based modeling through stochastic differential equations (SDEs) has provided a new perspective on diffusion models, and demonstrated superior performance on continuous data.

Optimal Scaling for Locally Balanced Proposals in Discrete Spaces

1 code implementation16 Sep 2022 Haoran Sun, Hanjun Dai, Dale Schuurmans

Optimal scaling has been well studied for Metropolis-Hastings (M-H) algorithms in continuous spaces, but a similar understanding has been lacking in discrete spaces.

Annealed Training for Combinatorial Optimization on Graphs

no code implementations23 Jul 2022 Haoran Sun, Etash K. Guha, Hanjun Dai

However, learning neural networks for CO problems is notoriously difficult in lack of the labeled data as the training is easily trapped at local optima.

Combinatorial Optimization

Discrete Langevin Sampler via Wasserstein Gradient Flow

no code implementations29 Jun 2022 Haoran Sun, Hanjun Dai, Bo Dai, Haomin Zhou, Dale Schuurmans

It is known that gradient-based MCMC samplers for continuous spaces, such as Langevin Monte Carlo (LMC), can be derived as particle versions of a gradient flow that minimizes KL divergence on a Wasserstein manifold.

To Supervise or Not: How to Effectively Learn Wireless Interference Management Models?

no code implementations28 Dec 2021 Bingqing Song, Haoran Sun, Wenqiang Pu, Sijia Liu, Mingyi Hong

We then provide a series of theoretical results to further understand the properties of the two approaches.


Multi-task Learning of Order-Consistent Causal Graphs

no code implementations NeurIPS 2021 Xinshi Chen, Haoran Sun, Caleb Ellington, Eric Xing, Le Song

We consider the problem of discovering $K$ related Gaussian directed acyclic graphs (DAGs), where the involved graph structures share a consistent causal order and sparse unions of supports.

Multi-Task Learning

CycleFlow: Purify Information Factors by Cycle Loss

no code implementations18 Oct 2021 Haoran Sun, Chen Chen, Lantian Li, Dong Wang

SpeechFlow is a powerful factorization model based on information bottleneck (IB), and its effectiveness has been reported by several studies.

Voice Conversion

Path Auxiliary Proposal for MCMC in Discrete Space

no code implementations ICLR 2022 Haoran Sun, Hanjun Dai, Wei Xia, Arun Ramamurthy

Energy-based Model (EBM) offers a powerful approach for modeling discrete structure, but both inference and learning of EBM are hard as it involves sampling from discrete distributions.

Provable Learning-based Algorithm For Sparse Recovery

no code implementations ICLR 2022 Xinshi Chen, Haoran Sun, Le Song

In this work, we propose PLISA (Provable Learning-based Iterative Sparse recovery Algorithm) to learn algorithms automatically from data.

Rolling Shutter Correction

Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment

4 code implementations16 Nov 2020 Haoran Sun, Wenqiang Pu, Minghe Zhu, Xiao Fu, Tsung-Hui Chang, Mingyi Hong

We propose to build the notion of continual learning (CL) into the modeling process of learning wireless systems, so that the learning model can incrementally adapt to the new episodes, {\it without forgetting} knowledge learned from the previous episodes.

Continual Learning Fairness

Deep generative factorization for speech signal

no code implementations27 Oct 2020 Haoran Sun, Lantian Li, Yunqi Cai, Yang Zhang, Thomas Fang Zheng, Dong Wang

Various information factors are blended in speech signals, which forms the primary difficulty for most speech information processing tasks.

On the Divergence of Decentralized Non-Convex Optimization

no code implementations20 Jun 2020 Mingyi Hong, Siliang Zeng, Junyu Zhang, Haoran Sun

However, by constructing some counter-examples, we show that when certain local Lipschitz conditions (LLC) on the local function gradient $\nabla f_i$'s are not satisfied, most of the existing decentralized algorithms diverge, even if the global Lipschitz condition (GLC) is satisfied, where the sum function $f$ has Lipschitz gradient.

Open-Ended Question Answering

On Investigation of Unsupervised Speech Factorization Based on Normalization Flow

no code implementations29 Oct 2019 Haoran Sun, Yunqi Cai, Lantian Li, Dong Wang

Speech signals are complex composites of various information, including phonetic content, speaker traits, channel effect, etc.

Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: A Joint Gradient Estimation and Tracking Approach

no code implementations13 Oct 2019 Haoran Sun, Songtao Lu, Mingyi Hong

Similarly, for online problems, the proposed method achieves an $\mathcal{O}(m \epsilon^{-3/2})$ sample complexity and an $\mathcal{O}(\epsilon^{-1})$ communication complexity, while the best existing bounds are $\mathcal{O}(m\epsilon^{-2})$ and $\mathcal{O}(\epsilon^{-2})$, respectively.

Stochastic Optimization

Alice's Adventures in the Markovian World

no code implementations21 Jul 2019 Zhanzhan Zhao, Haoran Sun

This paper proposes an algorithm Alice having no access to the physics law of the environment, which is actually linear with stochastic noise, and learns to make decisions directly online without a training phase or a stable policy as initial input.

Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms

no code implementations NeurIPS 2020 Xiangyi Chen, Tiancong Chen, Haoran Sun, Zhiwei Steven Wu, Mingyi Hong

We show that these algorithms are non-convergent whenever there is some disparity between the expected median and mean over the local gradients.

Federated Learning

Locating the boundaries of Pareto fronts: A Many-Objective Evolutionary Algorithm Based on Corner Solution Search

no code implementations8 Jun 2018 Xinye Cai, Haoran Sun, Chunyang Zhu, Zhenyu Li, Qingfu Zhang

In this paper, an evolutionary many-objective optimization algorithm based on corner solution search (MaOEA-CS) was proposed.

Cannot find the paper you are looking for? You can Submit a new open access paper.