Search Results for author:
Found 23 papers, 3 papers with code
Meta-Learning with Versatile Loss Geometries for Fast Adaptation Using Mirror Descent
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.
Contractive error feedback for gradient compression
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.
DPZero: Private Fine-Tuning of Language Models without Backpropagation
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
Sharpness-aware minimization (SAM) has well documented merits in enhancing generalization of deep neural networks, even without sizable data augmentation.
Conic Descent Redux for Memory-Efficient Optimization
Conic programming has well-documented merits in a gamut of signal processing and machine learning tasks.
Scalable Bayesian Meta-Learning through Generalized Implicit Gradients
Meta-learning owns unique effectiveness and swiftness in tackling emerging tasks with limited data.
Surrogate modeling for Bayesian optimization beyond a single Gaussian process
Tests on synthetic functions and real-world applications showcase the merits of the proposed method.
Distributionally Robust Semi-Supervised Learning Over Graphs
The data distribution is considered unknown, but lies within a Wasserstein ball centered around empirical data distribution.
Heavy Ball Momentum for Conditional Gradient
Conditional gradient, aka Frank Wolfe (FW) algorithms, have well-documented merits in machine learning and signal processing applications.
PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latex
This paper presents our solution for the ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX.
Adversarial Linear Contextual Bandits with Graph-Structured Side Observations
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.
Enhancing Parameter-Free Frank Wolfe with an Extra Subproblem
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.
Confusable Learning for Large-class Few-Shot Classification
Specifically, our method maintains a dynamically updating confusion matrix, which analyzes confusable classes in the dataset.
Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition
Thus, we propose a lightweight scene text recognition model named Hamming OCR.
How Does Momentum Help Frank Wolfe?
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
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
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
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
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
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
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
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
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.
