Search Results for author: Bingcong Li

Found 23 papers, 3 papers with code

Meta-Learning with Versatile Loss Geometries for Fast Adaptation Using Mirror Descent

1 code implementation20 Dec 2023 Yilang Zhang, Bingcong Li, Georgios B. Giannakis

Utilizing task-invariant prior knowledge extracted from related tasks, meta-learning is a principled framework that empowers learning a new task especially when data records are limited.

Few-Shot Learning

Contractive error feedback for gradient compression

no code implementations13 Dec 2023 Bingcong Li, Shuai Zheng, Parameswaran Raman, Anshumali Shrivastava, Georgios B. Giannakis

On-device memory concerns in distributed deep learning have become severe due to (i) the growth of model size in multi-GPU training, and (ii) the wide adoption of deep neural networks for federated learning on IoT devices which have limited storage.

Federated Learning Image Classification +2

DPZero: Private Fine-Tuning of Language Models without Backpropagation

no code implementations14 Oct 2023 Liang Zhang, Bingcong Li, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He

The widespread practice of fine-tuning large language models (LLMs) on domain-specific data faces two major challenges in memory and privacy.

Enhancing Sharpness-Aware Optimization Through Variance Suppression

1 code implementation NeurIPS 2023 Bingcong Li, Georgios B. Giannakis

Sharpness-aware minimization (SAM) has well documented merits in enhancing generalization of deep neural networks, even without sizable data augmentation.

Data Augmentation Image Classification +1

Conic Descent Redux for Memory-Efficient Optimization

no code implementations13 Aug 2023 Bingcong Li, Georgios B. Giannakis

Conic programming has well-documented merits in a gamut of signal processing and machine learning tasks.

Scalable Bayesian Meta-Learning through Generalized Implicit Gradients

1 code implementation31 Mar 2023 Yilang Zhang, Bingcong Li, Shijian Gao, Georgios B. Giannakis

Meta-learning owns unique effectiveness and swiftness in tackling emerging tasks with limited data.


Distributionally Robust Semi-Supervised Learning Over Graphs

no code implementations20 Oct 2021 Alireza Sadeghi, Meng Ma, Bingcong Li, Georgios B. Giannakis

The data distribution is considered unknown, but lies within a Wasserstein ball centered around empirical data distribution.

Heavy Ball Momentum for Conditional Gradient

no code implementations NeurIPS 2021 Bingcong Li, Alireza Sadeghi, Georgios B. Giannakis

Conditional gradient, aka Frank Wolfe (FW) algorithms, have well-documented merits in machine learning and signal processing applications.

Adversarial Linear Contextual Bandits with Graph-Structured Side Observations

no code implementations10 Dec 2020 Lingda Wang, Bingcong Li, Huozhi Zhou, Georgios B. Giannakis, Lav R. Varshney, Zhizhen Zhao

The second algorithm, \texttt{EXP3-LGC-IX}, is developed for a special class of problems, for which the regret is reduced to $\mathcal{O}(\sqrt{\alpha(G)dT\log{K}\log(KT)})$ for both directed as well as undirected feedback graphs.

Multi-Armed Bandits

Enhancing Parameter-Free Frank Wolfe with an Extra Subproblem

no code implementations9 Dec 2020 Bingcong Li, Lingda Wang, Georgios B. Giannakis, Zhizhen Zhao

Relying on no problem dependent parameters in the step sizes, the convergence rate of ExtraFW for general convex problems is shown to be ${\cal O}(\frac{1}{k})$, which is optimal in the sense of matching the lower bound on the number of solved FW subproblems.

Binary Classification Matrix Completion

Confusable Learning for Large-class Few-Shot Classification

no code implementations6 Nov 2020 Bingcong Li, Bo Han, Zhuowei Wang, Jing Jiang, Guodong Long

Specifically, our method maintains a dynamically updating confusion matrix, which analyzes confusable classes in the dataset.

Classification Few-Shot Image Classification +2

How Does Momentum Help Frank Wolfe?

no code implementations19 Jun 2020 Bingcong Li, Mario Coutino, Georgios B. Giannakis, Geert Leus

We unveil the connections between Frank Wolfe (FW) type algorithms and the momentum in Accelerated Gradient Methods (AGM).

Adaptive Step Sizes in Variance Reduction via Regularization

no code implementations15 Oct 2019 Bingcong Li, Georgios B. Giannakis

The main goal of this work is equipping convex and nonconvex problems with Barzilai-Borwein (BB) step size.

Nearly Optimal Algorithms for Piecewise-Stationary Cascading Bandits

no code implementations12 Sep 2019 Lingda Wang, Huozhi Zhou, Bingcong Li, Lav R. Varshney, Zhizhen Zhao

Cascading bandit (CB) is a popular model for web search and online advertising, where an agent aims to learn the $K$ most attractive items out of a ground set of size $L$ during the interaction with a user.

A Multistep Lyapunov Approach for Finite-Time Analysis of Biased Stochastic Approximation

no code implementations10 Sep 2019 Gang Wang, Bingcong Li, Georgios B. Giannakis

Motivated by the widespread use of temporal-difference (TD-) and Q-learning algorithms in reinforcement learning, this paper studies a class of biased stochastic approximation (SA) procedures under a mild "ergodic-like" assumption on the underlying stochastic noise sequence.


Almost Tune-Free Variance Reduction

no code implementations ICML 2020 Bingcong Li, Lingda Wang, Georgios B. Giannakis

Then a simple yet effective means to adjust the number of iterations per inner loop is developed to enhance the merits of the proposed averaging schemes and BB step sizes.

On the Convergence of SARAH and Beyond

no code implementations5 Jun 2019 Bingcong Li, Meng Ma, Georgios B. Giannakis

For convex problems, when adopting an $n$-dependent step size, the complexity of L2S is ${\cal O}(n+ \sqrt{n}/\epsilon)$; while for more frequently adopted $n$-independent step size, the complexity is ${\cal O}(n+ n/\epsilon)$.

Revisiting Sample Selection Approach to Positive-Unlabeled Learning: Turning Unlabeled Data into Positive rather than Negative

no code implementations29 Jan 2019 Miao Xu, Bingcong Li, Gang Niu, Bo Han, Masashi Sugiyama

May there be a new sample selection method that can outperform the latest importance reweighting method in the deep learning age?


Bandit Online Learning with Unknown Delays

no code implementations9 Jul 2018 Bingcong Li, Tianyi Chen, Georgios B. Giannakis

This paper deals with bandit online learning problems involving feedback of unknown delay that can emerge in multi-armed bandit (MAB) and bandit convex optimization (BCO) settings.

Secure Mobile Edge Computing in IoT via Collaborative Online Learning

no code implementations9 May 2018 Bingcong Li, Tianyi Chen, Georgios B. Giannakis

To accommodate heterogeneous tasks in Internet of Things (IoT), a new communication and computing paradigm termed mobile edge computing emerges that extends computing services from the cloud to edge, but at the same time exposes new challenges on security.


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