Search Results for author:
Found 48 papers, 8 papers with code
Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking
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 $\mathcal{O}(\epsilon^{-2})$.
Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks
In this paper, we study the problem of constrained min-max optimization in a black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values.
Training Nonlinear Transformers for Efficient In-Context Learning: A Theoretical Learning and Generalization Analysis
Despite the empirical success, the mechanics of how to train a Transformer to achieve ICL and the corresponding ICL capacity is mostly elusive due to the technical challenges of analyzing the nonconvex training problems resulting from the nonlinear self-attention and nonlinear activation in Transformers.
Decentralized Bilevel Optimization over Graphs: Loopless Algorithmic Update and Transient Iteration Complexity
In this paper, we introduce a single-loop decentralized SBO (D-SOBA) algorithm and establish its transient iteration complexity, which, for the first time, clarifies the joint influence of network topology and data heterogeneity on decentralized bilevel algorithms.
Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization
In this paper, we present a novel bilevel optimization-based training approach to training acoustic models for automatic speech recognition (ASR) tasks that we term {bi-level joint unsupervised and supervised training (BL-JUST)}.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Soft Random Sampling: A Theoretical and Empirical Analysis
Soft random sampling (SRS) is a simple yet effective approach for efficient training of large-scale deep neural networks when dealing with massive data.
Ontology Revision based on Pre-trained Language Models
We conduct experiments over 19 ontology pairs and compare our algorithms and scoring functions with existing ones.
On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $ε$-Greedy Exploration
This paper provides the first theoretical convergence and sample complexity analysis of the practical setting of DQNs with $\epsilon$-greedy policy.
FedLogic: Interpretable Federated Multi-Domain Chain-of-Thought Prompt Selection for Large Language Models
To improve interpretability and explore the balance principle between generality and personalization under a multi-domain CoT prompt selection scenario, we propose the Federated Logic rule learning approach (FedLogic).
How Can Context Help? Exploring Joint Retrieval of Passage and Personalized Context
The integration of external personalized context information into document-grounded conversational systems has significant potential business value, but has not been well-studied.
A Generalized Alternating Method for Bilevel Learning under the Polyak-Łojasiewicz Condition
Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning.
PRECISION: Decentralized Constrained Min-Max Learning with Low Communication and Sample Complexities
Decentralized min-max optimization problems with domain constraints underpins many important ML applications, including multi-agent ML fairness assurance, and policy evaluations in multi-agent reinforcement learning.
Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks
Due to the significant computational challenge of training large-scale graph neural networks (GNNs), various sparse learning techniques have been exploited to reduce memory and storage costs.
Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimization
In this paper, we design and analyze stochastic inexact augmented Lagrangian methods (Stoc-iALM) to solve problems involving a nonconvex composite (i. e. smooth+nonsmooth) objective and nonconvex smooth functional constraints.
ASGNN: Graph Neural Networks with Adaptive Structure
In this work, we propose a novel interpretable message passing scheme with adaptive structure (ASMP) to defend against adversarial attacks on graph structure.
INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks
Our main contributions in this paper are two-fold: i) We first propose a deterministic algorithm called INTERACT (inner-gradient-descent-outer-tracked-gradient) that requires the sample complexity of $\mathcal{O}(n \epsilon^{-1})$ and communication complexity of $\mathcal{O}(\epsilon^{-1})$ to solve the bilevel optimization problem, where $n$ and $\epsilon > 0$ are the number of samples at each agent and the desired stationarity gap, respectively.
A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization
The GDPA is a primal-dual algorithm, which only exploits the first-order information of both the objective and constraint functions to update the primal and dual variables in an alternating way.
Understanding Benign Overfitting in Gradient-Based Meta Learning
While the conventional statistical learning theory suggests that overparameterized models tend to overfit, empirical evidence reveals that overparameterized meta learning methods still work well -- a phenomenon often called "benign overfitting."
Distributed Adversarial Training to Robustify Deep Neural Networks at Scale
Spurred by that, we propose distributed adversarial training (DAT), a large-batch adversarial training framework implemented over multiple machines.
Min-Max Bilevel Multi-objective Optimization with Applications in Machine Learning
We consider a generic min-max multi-objective bilevel optimization problem with applications in robust machine learning such as representation learning and hyperparameter optimization.
Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning
To our knowledge, this paper is the first work that achieves both $\mathcal{O}(\epsilon^{-2})$ sample complexity and $\mathcal{O}(\epsilon^{-2})$ communication complexity in decentralized policy evaluation for cooperative MARL.
Multi-agent Reinforcement Learning
Reinforcement Learning (RL)
+1
Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward
In this paper, we establish the first finite-time convergence result of the actor-critic algorithm for fully decentralized multi-agent reinforcement learning (MARL) problems with average reward.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective
Under this model, latent correlation maximization is shown to guarantee the extraction of the shared components across views (up to certain ambiguities).
Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition
Deep neural networks have been shown as a class of useful tools for addressing signal recognition issues in recent years, especially for identifying the nonlinear feature structures of signals.
An Efficient Learning Framework For Federated XGBoost Using Secret Sharing And Distributed Optimization
XGBoost is one of the most widely used machine learning models in the industry due to its superior learning accuracy and efficiency.
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
Large-scale distributed training of Deep Neural Networks (DNNs) on state-of-the-art platforms is expected to be severely communication constrained.
Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine Learning
In this paper, we propose a framework of generating adversarial examples for unsupervised models and demonstrate novel applications to data augmentation.
Federated Acoustic Modeling For Automatic Speech Recognition
In this paper, we investigate federated acoustic modeling using data from multiple clients.
Federated Learning
Speech Recognition
Sound
Distributed, Parallel, and Cluster Computing
Audio and Speech Processing
Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems
To the best of our knowledge, this is the first time that first-order algorithms with polynomial per-iteration complexity and global sublinear rate are designed to find SOSPs of the important class of non-convex problems with linear constraints (almost surely).
Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis
The present contribution deals with decentralized policy evaluation in multi-agent Markov decision processes using temporal-difference (TD) methods with linear function approximation for scalability.
Overcoming Catastrophic Forgetting via Direction-Constrained Optimization
We study the principal directions of the trajectory of the optimizer after convergence and show that traveling along a few top principal directions can quickly bring the parameters outside the cone but this is not the case for the remaining directions.
Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations
The resulting scheme for meta-learning a UAP generator (i) has better performance (50% higher ASR) than baselines such as Projected Gradient Descent, (ii) has better performance (37% faster) than the vanilla L2O and MAML frameworks (when applicable), and (iii) is able to simultaneously handle UAP generation for different victim models and image data sources.
Non-convex Min-Max Optimization: Applications, Challenges, and Recent Theoretical Advances
The min-max optimization problem, also known as the saddle point problem, is a classical optimization problem which is also studied in the context of zero-sum games.
Randomized Bregman Coordinate Descent Methods for Non-Lipschitz Optimization
Further, we show that the iteration complexity of the proposed method is $O(n\varepsilon^{-2})$ to achieve $\epsilon$-stationary point, where $n$ is the number of blocks of coordinates.
Distributed Learning in the Non-Convex World: From Batch to Streaming Data, and Beyond
In particular, we {provide a selective review} about the recent techniques developed for optimizing non-convex models (i. e., problem classes), processing batch and streaming data (i. e., data types), over the networks in a distributed manner (i. e., communication and computation paradigm).
Leveraging Two Reference Functions in Block Bregman Proximal Gradient Descent for Non-convex and Non-Lipschitz Problems
In the applications of signal processing and data analytics, there is a wide class of non-convex problems whose objective function is freed from the common global Lipschitz continuous gradient assumption (e. g., the nonnegative matrix factorization (NMF) problem).
Learn Electronic Health Records by Fully Decentralized Federated Learning
Federated learning opens a number of research opportunities due to its high communication efficiency in distributed training problems within a star network.
No-regret Non-convex Online Meta-Learning
The online meta-learning framework is designed for the continual lifelong learning setting.
Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: A Joint Gradient Estimation and Tracking Approach
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.
Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML
In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values.
SNAP: Finding Approximate Second-Order Stationary Solutions Efficiently for Non-convex Linearly Constrained Problems
This paper proposes low-complexity algorithms for finding approximate second-order stationary points (SOSPs) of problems with smooth non-convex objective and linear constraints.
Understand the dynamics of GANs via Primal-Dual Optimization
By developing new primal-dual optimization tools, we show that, with a proper stepsize choice, the widely used first-order iterative algorithm in training GANs would in fact converge to a stationary solution with a sublinear rate.
Signal Demodulation with Machine Learning Methods for Physical Layer Visible Light Communications: Prototype Platform, Open Dataset and Algorithms
The dataset is available online, which contains eight types of modulated signals.
Deep Learning for Signal Demodulation in Physical Layer Wireless Communications: Prototype Platform, Open Dataset, and Analytics
In this paper, we investigate deep learning (DL)-enabled signal demodulation methods and establish the first open dataset of real modulated signals for wireless communication systems.
Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications
In this work, we consider a block-wise one-sided non-convex min-max problem, in which the minimization problem consists of multiple blocks and is non-convex, while the maximization problem is (strongly) concave.
Power Market Price Forecasting via Deep Learning
Then the raw input and output data are preprocessed by unit scaling, and the trained network is tested on the real price data under different input lengths, forecasting horizons and data sizes.
On the Sublinear Convergence of Randomly Perturbed Alternating Gradient Descent to Second Order Stationary Solutions
The alternating gradient descent (AGD) is a simple but popular algorithm which has been applied to problems in optimization, machine learning, data ming, and signal processing, etc.
A Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization: Convergence Analysis and Optimality
The proposed algorithm is guaranteed to converge to the set of Karush-Kuhn-Tucker (KKT) points of the nonconvex SymNMF problem.
