Search Results for author:
Found 91 papers, 17 papers with code
Advancing Model Pruning via Bi-level Optimization
To reduce the computation overhead, various efficient 'one-shot' pruning methods have been developed, but these schemes are usually unable to find winning tickets as good as IMP.
Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment
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.
Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
To recover the `clustering-friendly' latent representations and to better cluster the data, we propose a joint DR and K-means clustering approach in which DR is accomplished via learning a deep neural network (DNN).
Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization
We first show that the commonly-used Fast-AT is equivalent to using a stochastic gradient algorithm to solve a linearized BLO problem involving a sign operation.
Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification.
ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
In this paper, we propose a zeroth-order AdaMM (ZO-AdaMM) algorithm, that generalizes AdaMM to the gradient-free regime.
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
To tackle this problem, we next propose to prepend an autoencoder (AE) to a given (black-box) model so that DS can be trained using variance-reduced ZO optimization.
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
In the evolving landscape of natural language processing (NLP), fine-tuning pre-trained Large Language Models (LLMs) with first-order (FO) optimizers like SGD and Adam has become standard.
Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective
However, it is often challenging for these approaches to learn in a dynamic environment.
Learned Conjugate Gradient Descent Network for Massive MIMO Detection
Furthermore, in order to reduce the memory costs, a novel quantized LcgNet is proposed, where a low-resolution nonuniform quantizer is integrated into the LcgNet to smartly quantize the aforementioned step-sizes.
FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data
Aiming at designing FL algorithms that are provably fast and require as few assumptions as possible, we propose a new algorithm design strategy from the primal-dual optimization perspective.
Decentralized Riemannian Gradient Descent on the Stiefel Manifold
The global function is represented as a finite sum of smooth local functions, where each local function is associated with one agent and agents communicate with each other over an undirected connected graph.
When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning
Offline inverse reinforcement learning (Offline IRL) aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent.
Deep Spectrum Cartography: Completing Radio Map Tensors Using Learned Neural Models
However, such deep learning (DL)-based SC approaches encounter serious challenges in both off-line model learning (training) and completion (generalization), possibly because the latent state space for generating the radio maps is prohibitively large.
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.
Parallel Successive Convex Approximation for Nonsmooth Nonconvex Optimization
In this work, we propose an inexact parallel BCD approach where at each iteration, a subset of the variables is updated in parallel by minimizing convex approximations of the original objective function.
Optimization and Control
A Bayesian Approach to Robust Inverse Reinforcement Learning
We consider a Bayesian approach to offline model-based inverse reinforcement learning (IRL).
Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization
Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Zeroth Order Nonconvex Multi-Agent Optimization over Networks
In this paper, we consider distributed optimization problems over a multi-agent network, where each agent can only partially evaluate the objective function, and it is allowed to exchange messages with its immediate neighbors.
Structured SUMCOR Multiview Canonical Correlation Analysis for Large-Scale Data
In this work, we propose a new computational framework for large-scale SUMCOR GCCA that can easily incorporate a suite of structural regularizers which are frequently used in data analytics.
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.
On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don't Worry About Its Nonsmooth Loss Function
Many machine learning techniques sacrifice convenient computational structures to gain estimation robustness and modeling flexibility.
On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization
In particular, we first show that for a family of quadratic minimization problems, the iteration complexity $\mathcal{O}(\log^2(p)\cdot\log(1/\epsilon))$ of the CBCD-type methods matches that of the GD methods in term of dependency on $p$, up to a $\log^2 p$ factor.
Scalable and Flexible Multiview MAX-VAR Canonical Correlation Analysis
Generalized canonical correlation analysis (GCCA) aims at finding latent low-dimensional common structure from multiple views (feature vectors in different domains) of the same entities.
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.
NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization
We study a stochastic and distributed algorithm for nonconvex problems whose objective consists of a sum of $N$ nonconvex $L_i/N$-smooth functions, plus a nonsmooth regularizer.
Asynchronous Distributed ADMM for Large-Scale Optimization- Part I: Algorithm and Convergence Analysis
By formulating the learning problem as a consensus problem, the ADMM can be used to solve the consensus problem in a fully parallel fashion over a computer network with a star topology.
Alternating direction method of multipliers for penalized zero-variance discriminant analysis
To accomplish this task, we propose a heuristic, called sparse zero-variance discriminant analysis (SZVD), for simultaneously performing linear discriminant analysis and feature selection on high dimensional data.
Asynchronous Distributed ADMM for Large-Scale Optimization- Part II: Linear Convergence Analysis and Numerical Performance
Unfortunately, a direct synchronous implementation of such algorithm does not scale well with the problem size, as the algorithm speed is limited by the slowest computing nodes.
On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization
We prove that under our derived conditions, these methods can achieve the convergence rate of order $O(\log{T}/\sqrt{T})$ for nonconvex stochastic optimization.
Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks
In this paper we consider nonconvex optimization and learning over a network of distributed nodes.
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks
In this work, we study two first-order primal-dual based algorithms, the Gradient Primal-Dual Algorithm (GPDA) and the Gradient Alternating Direction Method of Multipliers (GADMM), for solving a class of linearly constrained non-convex optimization problems.
signSGD via Zeroth-Order Oracle
Our study shows that ZO signSGD requires $\sqrt{d}$ times more iterations than signSGD, leading to a convergence rate of $O(\sqrt{d}/\sqrt{T})$ under mild conditions, where $d$ is the number of optimization variables, and $T$ is the number of iterations.
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.
On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator
We study the global convergence of generative adversarial imitation learning for linear quadratic regulators, which is posed as minimax optimization.
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.
Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
We show that these algorithms are non-convergent whenever there is some disparity between the expected median and mean over the local gradients.
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.
On the Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost
Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind.
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.
Variance Reduced Policy Evaluation with Smooth Function Approximation
Policy evaluation with smooth and nonlinear function approximation has shown great potential for reinforcement learning.
Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost
Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind.
Dense Recurrent Neural Networks for Accelerated MRI: History-Cognizant Unrolling of Optimization Algorithms
These methods unroll iterative optimization algorithms to solve the inverse problem objective function, by alternating between domain-specific data consistency and data-driven regularization via neural networks.
A Communication Efficient Collaborative Learning Framework for Distributed Features
We introduce a collaborative learning framework allowing multiple parties having different sets of attributes about the same user to jointly build models without exposing their raw data or model parameters.
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).
A Unified Convergence Analysis of Block Successive Minimization Methods for Nonsmooth Optimization
The block coordinate descent (BCD) method is widely used for minimizing a continuous function f of several block variables.
Optimization and Control
Stochastic Proximal Gradient Consensus Over Random Networks
We consider solving a convex, possibly stochastic optimization problem over a randomly time-varying multi-agent network.
Optimization and Control Information Theory Information Theory
On the Divergence of Decentralized Non-Convex Optimization
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.
Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds
We obtain this rate by providing the first analyses on a collection of private gradient-based methods, including adaptive algorithms DP RMSProp and DP Adam.
Understanding Gradient Clipping in Private SGD: A Geometric Perspective
Deep learning models are increasingly popular in many machine learning applications where the training data may contain sensitive information.
A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic
Bilevel optimization is a class of problems which exhibit a two-level structure, and its goal is to minimize an outer objective function with variables which are constrained to be the optimal solution to an (inner) optimization problem.
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.
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.
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 $\mathcal{O}(\epsilon^{-2})$.
RMSprop can converge with proper hyper-parameter
Removing this assumption allows us to establish a phase transition from divergence to non-divergence for RMSProp.
Learning to Beamform in Heterogeneous Massive MIMO Networks
It is well-known that the problem of finding the optimal beamformers in massive multiple-input multiple-output (MIMO) networks is challenging because of its non-convexity, and conventional optimization based algorithms suffer from high computational costs.
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).
Provably Efficient Neural GTD for Off-Policy Learning
This paper studies a gradient temporal difference (GTD) algorithm using neural network (NN) function approximators to minimize the mean squared Bellman error (MSBE).
Spectrum Cartography via Coupled Block-Term Tensor Decomposition
Spectrum cartography aims at estimating power propagation patterns over a geographical region across multiple frequency bands (i. e., a radio map)---from limited samples taken sparsely over the region.
Joint Channel Assignment and Power Allocation for Multi-UAV Communication
Unmanned aerial vehicle (UAV) swarm has emerged as a promising novel paradigm to achieve better coverage and higher capacity for future wireless network by exploiting the more favorable line-of-sight (LoS) propagation.
Hybrid Federated Learning: Algorithms and Implementation
To the best of our knowledge, this is the first formulation and algorithm developed for the hybrid FL.
Towards Understanding Asynchronous Advantage Actor-critic: Convergence and Linear Speedup
Asynchronous and parallel implementation of standard reinforcement learning (RL) algorithms is a key enabler of the tremendous success of modern RL.
On the Local Linear Rate of Consensus on the Stiefel Manifold
We study the convergence properties of Riemannian gradient method for solving the consensus problem (for an undirected connected graph) over the Stiefel manifold.
A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum
We focus on bilevel problems where the lower level subproblem is strongly-convex and the upper level objective function is smooth.
On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations
Although deep learning (DL) has received much attention in accelerated MRI, recent studies suggest small perturbations may lead to instabilities in DL-based reconstructions, leading to concern for their clinical application.
Stochastic Mirror Descent for Low-Rank Tensor Decomposition Under Non-Euclidean Losses
This work offers a unified stochastic algorithmic framework for large-scale CPD decomposition under a variety of non-Euclidean loss functions.
STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning
Despite extensive research, for a generic non-convex FL problem, it is not clear, how to choose the WNs' and the server's update directions, the minibatch sizes, and the local update frequency, so that the WNs use the minimum number of samples and communication rounds to achieve the desired solution.
Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
Recently, there has been a line of work on incorporating the formal privacy notion of differential privacy with FL.
Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence
To regulate a social system comprised of self-interested agents, economic incentives are often required to induce a desirable outcome.
Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach
We analyze the optimization and the generalization performance of the proposed framework for the $\ell_2$ loss.
Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees
The flexibility in our design allows the proposed MARL-CAC algorithm to be used in a {\it fully decentralized} setting, where the agents can only communicate with their neighbors, as well as a {\it federated} setting, where the agents occasionally communicate with a server while optimizing their (partially personalized) local models.
Dynamic Differential-Privacy Preserving SGD
The equivalent privacy costs controlled by maintaining the same gradient clipping thresholds and noise powers in each step result in unstable updates and a lower model accuracy when compared to the non-DP counterpart.
To Supervise or Not: How to Effectively Learn Wireless Interference Management Models?
We then provide a series of theoretical results to further understand the properties of the two approaches.
Understanding A Class of Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective
Distributed algorithms have been playing an increasingly important role in many applications such as machine learning, signal processing, and control.
Zeroth-Order SciML: Non-intrusive Integration of Scientific Software with Deep Learning
Existing knowledge integration approaches are limited to using differentiable knowledge source to be compatible with first-order DL training paradigm.
Optimal Solutions for Joint Beamforming and Antenna Selection: From Branch and Bound to Graph Neural Imitation Learning
This work revisits the joint beamforming (BF) and antenna selection (AS) problem, as well as its robust beamforming (RBF) version under imperfect channel state information (CSI).
A Framework for Understanding Model Extraction Attack and Defense
The privacy of machine learning models has become a significant concern in many emerging Machine-Learning-as-a-Service applications, where prediction services based on well-trained models are offered to users via pay-per-query.
Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees
Other approaches in the inverse reinforcement learning (IRL) literature emphasize policy estimation at the expense of reduced reward estimation accuracy.
Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees
To reduce the computational burden of a nested loop, novel methods such as SQIL [1] and IQ-Learn [2] emphasize policy estimation at the expense of reward estimation accuracy.
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work
Third, we consider a constrained optimization formulation where the feasible region is the nice local region, and prove that every KKT point is a nearly global minimizer.
On the Robustness of deep learning-based MRI Reconstruction to image transformations
We find a new instability source of MRI image reconstruction, i. e., the lack of reconstruction robustness against spatial transformations of an input, e. g., rotation and cutout.
What Is Missing in IRM Training and Evaluation? Challenges and Solutions
We propose a new IRM variant to address this limitation based on a novel viewpoint of ensemble IRM games as consensus-constrained bi-level optimization.
GLASU: A Communication-Efficient Algorithm for Federated Learning with Vertically Distributed Graph Data
In this paper, we propose a model splitting method that splits a backbone GNN across the clients and the server and a communication-efficient algorithm, GLASU, to train such a model.
An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning
Overall, we hope that this article can serve to accelerate the adoption of BLO as a generic tool to model, analyze, and innovate on a wide array of emerging SP and ML applications.
Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety.
Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
In our work, we propose a new error-feedback (EF) DP algorithm as an alternative to DPSGD-GC, which not only offers a diminishing utility bound without inducing a constant clipping bias, but more importantly, it allows for an arbitrary choice of clipping threshold that is independent of the problem.
Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate
In this paper, we introduce a novel subspace cubic regularized Newton method that achieves a dimension-independent global convergence rate of ${O}\left(\frac{1}{mk}+\frac{1}{k^2}\right)$ for solving convex optimization problems.
MADA: Meta-Adaptive Optimizers through hyper-gradient Descent
Since Adam was introduced, several novel adaptive optimizers for deep learning have been proposed.
Pre-training Differentially Private Models with Limited Public Data
The superior performance of large foundation models relies on the use of massive amounts of high-quality data, which often contain sensitive, private and copyrighted material that requires formal protection.
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
Subsequently, we employ a classifier that is jointly trained with the watermark to detect the presence of the watermark.
EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence
We follow the global contrastive learning loss as introduced in SogCLR, and propose EMC$^2$ which utilizes an adaptive Metropolis-Hastings subroutine to generate hardness-aware negative samples in an online fashion during the optimization.
