Search Results for author: Haotian Jiang

Found 11 papers, 1 papers with code

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

1 code implementation4 Mar 2024 Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin A Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin

Lin et al. (2024) recently introduced the Private Evolution (PE) algorithm to generate DP synthetic images with only API access to diffusion models.

Privacy Preserving

Forward and Inverse Approximation Theory for Linear Temporal Convolutional Networks

no code implementations29 May 2023 Haotian Jiang, Qianxiao Li

We present a theoretical analysis of the approximation properties of convolutional architectures when applied to the modeling of temporal sequences.

Temporal Sequences

Approximation Rate of the Transformer Architecture for Sequence Modeling

no code implementations29 May 2023 Haotian Jiang, Qianxiao Li

The Transformer architecture is widely applied in sequence modeling applications, yet the theoretical understanding of its working principles remains limited.

Learning across Data Owners with Joint Differential Privacy

no code implementations25 May 2023 Yangsibo Huang, Haotian Jiang, Daogao Liu, Mohammad Mahdian, Jieming Mao, Vahab Mirrokni

In this paper, we study the setting in which data owners train machine learning models collaboratively under a privacy notion called joint differential privacy [Kearns et al., 2018].

Multi-class Classification

A Brief Survey on the Approximation Theory for Sequence Modelling

no code implementations27 Feb 2023 Haotian Jiang, Qianxiao Li, Zhong Li, Shida Wang

We survey current developments in the approximation theory of sequence modelling in machine learning.

Decomposable Non-Smooth Convex Optimization with Nearly-Linear Gradient Oracle Complexity

no code implementations7 Aug 2022 Sally Dong, Haotian Jiang, Yin Tat Lee, Swati Padmanabhan, Guanghao Ye

In this work, we give an algorithm that minimizes the above convex formulation to $\epsilon$-accuracy in $\widetilde{O}(\sum_{i=1}^n d_i \log (1 /\epsilon))$ gradient computations, with no assumptions on the condition number.

On the approximation properties of recurrent encoder-decoder architectures

no code implementations ICLR 2022 Zhong Li, Haotian Jiang, Qianxiao Li

Our results provide the theoretical understanding of approximation properties of the recurrent encoder-decoder architecture, which characterises, in the considered setting, the types of temporal relationships that can be efficiently learned.

Approximation Theory of Convolutional Architectures for Time Series Modelling

no code implementations20 Jul 2021 Haotian Jiang, Zhong Li, Qianxiao Li

We study the approximation properties of convolutional architectures applied to time series modelling, which can be formulated mathematically as a functional approximation problem.

Time Series Time Series Analysis

An Improved Cutting Plane Method for Convex Optimization, Convex-Concave Games and its Applications

no code implementations8 Apr 2020 Haotian Jiang, Yin Tat Lee, Zhao Song, Sam Chiu-wai Wong

We propose a new cutting plane algorithm that uses an optimal $O(n \log (\kappa))$ evaluations of the oracle and an additional $O(n^2)$ time per evaluation, where $\kappa = nR/\epsilon$.

Practical Algorithms for Best-K Identification in Multi-Armed Bandits

no code implementations19 May 2017 Haotian Jiang, Jian Li, Mingda Qiao

In the Best-$K$ identification problem (Best-$K$-Arm), we are given $N$ stochastic bandit arms with unknown reward distributions.

Multi-Armed Bandits

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