Related papers: DOMAC: Differentiable Optimization for High-Speed …
Many theoretical and experimental studies have used heuristic methods to investigate the dynamic behaviour of the passive coupling of adjacent structures. However, few papers have used optimization techniques with guaranteed convergence in…
We present a hierarchical optimization architecture for large-scale power networks that overcomes limitations of fully centralized and fully decentralized architectures. The architecture leverages principles of multigrid computing schemes,…
Mixup is an efficient data augmentation approach that improves the generalization of neural networks by smoothing the decision boundary with mixed data. Recently, dynamic mixup methods have improved previous static policies effectively…
Specialized hardware accelerators are becoming important for more and more applications. Thanks to specialization, they can achieve high performance and energy efficiency but their design is complex and time consuming. This problem is…
This paper considers an optimization problem that components of the objective function are available at different nodes of a network and nodes are allowed to only exchange information with their neighbors. The decentralized alternating…
In this work and its accompanying Part II [1], we develop an accelerated algorithmic framework, DAMA (Decentralized Accelerated Minimax Approach), for nonconvex Polyak-Lojasiewicz minimax optimization over decentralized multi-agent…
Digital memcomputing machines (DMMs) are a class of computational machines designed to solve combinatorial optimization problems. A practical realization of DMMs can be accomplished via electrical circuits of highly non-linear,…
This paper considers decentralized consensus optimization problems where nodes of a network have access to different summands of a global objective function. Nodes cooperate to minimize the global objective by exchanging information with…
Topology optimization (TO) is a family of computational methods that derive near-optimal geometries from formal problem descriptions. Despite their success, established TO methods are limited to generating single solutions, restricting the…
Alternating Direction Method of Multiplier (ADMM) has been a popular algorithmic framework for separable optimization problems with linear constraints. For numerical ADMM fail to exploit the particular structure of the problem at hand nor…
As deep learning continues to advance and is applied to increasingly complex scenarios, the demand for concurrent deployment of multiple neural network models has arisen. This demand, commonly referred to as multi-tenant computing, is…
In this thesis, we aim to improve the performance of TAMP algorithms from three complementary perspectives. First, we investigate the integration of discrete task planning with continuous trajectory optimization. Our main contribution is a…
This paper explores the multi-access distributed computing (MADC) model, a novel distributed computing framework where mapper and reducer nodes are distinct entities. Unlike traditional MapReduce frameworks, MADC leverages coding-theoretic…
In recent years, processing in memory (PIM) based mixedsignal designs have been proposed as energy- and area-efficient solutions with ultra high throughput to accelerate DNN computations. However, PIM designs are sensitive to imperfections…
Dynamic programming is a powerful technique that is, unfortunately, often inherently sequential. That is, there exists no unified method to parallelize algorithms that use dynamic programming. In this paper, we attempt to address this issue…
Slow working nodes, known as stragglers, can greatly reduce the speed of distributed computation. Coded matrix multiplication is a recently introduced technique that enables straggler-resistant distributed multiplication of large matrices.…
The common pipeline of training deep neural networks consists of several building blocks such as data augmentation and network architecture selection. AutoML is a research field that aims at automatically designing those parts, but most…
The sample-inefficiency problem in Artificial Intelligence refers to the inability of current Deep Reinforcement Learning models to optimize action policies within a small number of episodes. Recent studies have tried to overcome this…
Large-scale deep learning models for physical AI applications depend on diverse training data collection efforts. These models and correspondingly, the training data, must address different evaluation criteria necessary for the models to be…
Model Predictive Control (MPC) is a computationally demanding control technique that allows dealing with multiple-input and multiple-output systems, while handling constraints in a systematic way. The necessity of solving an optimization…