Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 30 for “"Min-Max optimization"”.
-
Convergence in min-max optimization
Min-max optimization is a classic problem with applications in constrained optimization, robust optimization, and game theory. This dissertation covers new convergence rate results in min-max optimization. We show that the classic fictitious play dynamic with lexicographic tiebreaking converges …
-
Provably effective algorithms for min-max optimization
… machine learning tasks can be formulated as min-max optimization. This motivates us to design effective and efficient first-order methods that provably converge to the global min-max points. For this purpose, this thesis focuses on designing practical algorithms for several specific machine …
-
Next-Generation Iterative Algorithms for Large-scale Min-max Optimization: Design and Analysis
… the design of algorithms for solving min-max optimization problems, which form the mathematical foundation of many modern applications in machine learning, game theory, and optimization. This work offers new theoretical insights and practical algorithms that address the limitations of …
-
Convergence Rates of Gradient Descent-ascent Dynamics under Computation Constraints in Solving Min-max Optimization
… Descent-ascent (GDA) method for solving the Min-max optimization (MMO) problems under computation constraints. In particular, we focus our study on two main classes of MMO: a continuous-time variant of the centralized Min-max problem where the GDA update only has access to the gradients of …
-
Evaluating Adversarial Learning on Different Types of Deep Learning-based Intrusion Detection Systems using min-max optimization
… recurrent neural networks. We utilize the min-max approach to formulate the problem of training robustness intrusion detection against adversarial samples using UNSW-NB15 and NSD-KDD. We structure an optimization framework by applying the max approach to generate persuasive adversarial …
-
EXPERIMENTAL EVALUATION OF ITERATIVE METHODS FOR GAMES
Min-max optimization problems are a class of problems that are usually seen in game theory, machine learning, deep learning, and adversarial training. Deterministic gradient methods, such as gradient descent ascent (GDA), Extragradient (EG), and Hamiltonian Gradient Descent (HGD) are usually …
-
Algorithms and Theory for Saddle Point Problems with Relaxed Structural Conditions
Saddle point, also known as min--max, optimization considers problems in which one variable is minimized while another is maximized, typically through an objective that couples the two variables. These problems arise naturally in areas including game theory, robust optimization, and adversarial …
-
PER PLAYER LOCAL EXTRAGRADIENT IN MULTIPLAYER FEDERATED LEARNING: CONVERGENCE GUARANTEES AND PRACTICAL PERFORMANCE
… many machine learning models is formulated as a minimization problem, where the goal is to learn a model that minimizes a loss function over data. In recent years, however, the machine learning community has become increasingly interested in more challenging min-max optimization problems and …
-
Biomechanical analysis of asymmetric and dynamic lifting task
… hand loads. An infinite order polynomial (min/max) optimization criterion predicted percentage of maximum muscle forces, which achieved 98% correlation with normalized EMG. In a separate study, motion data during lifting of 13.6 kg (30 lb) weight at 0 , 30 and 60 asymmetry was collected by …
-
Extragradient-type Methods for (L0, L1)-Lipschitz Variational Inequality Problems
… inequality problems (VIPs) capture a variety of optimization problems of interest for current machine learning tasks, including min-max optimization and finding game equilibria. These problems are commonly solved using first-order iterative methods known as extragradient-type algorithms. …
-
Optimized Thruster Allocation Utilizing Dual Quaternions for the Asteroid Sample Return Mission (OSIRIS-REx)
… frames. The developed method is based on a min-max optimization that results in a constant thruster distribution matrix. From the optimization, a minimum thrust solution is calculated for the coupled position and attitude commands. Therefore, its integration into the dual quaternion dynamics …
-
Discrete and Continuous Optimization for Collaborative and Multi-task Learning
… challenges of robust collaborative learning and optimization in both discrete and continuous domains. With the ever-increasing scale of data and the growing demand for effective distributed learning, a multitude of obstacles emerge, including communication limitations, resilience to failures and …
-
Event-triggered near optimal adaptive control of interconnected systems
… are considered as non-cooperative players and a min-max optimization problem is formulated for linear and affine nonlinear systems by using zero-sum game approach for simultaneous optimization of both the control policy and the event based sampling instants. The net result is the development of …
-
Robust and scalable deep learning for cyber-physical systems
… (ML)-enabled cyber-physical systems are becoming prevalent in various sectors of modern society. Although machine (deep) learning systems have been very beneficial in many applications and made significant improvements possible in CPS, it is important to investigate the resilience and …
-
Control Studies of DFIG based Wind Power Systems
… the need of voltage control to maintain the terminal voltage of a wind plant to make it a PV bus like conventional generators with excitation control. In the literature with PI controllers used, the parameters of PI controllers need to be tuned as a tradeoff or compromise among various operating …
-
Bioenergy supply chain optimization - decision making under uncertainty
… methodology and algorithms for solving complex optimization problems frequently encountered in the procurement of biomass for bioenergy production. Uncertainty and randomness is predominant, although often ignored, throughout the biomass supply chain. Uncertainty in the biomass supply chain may …
-
Model Predictive Control for UAGV Path Tracking in the Presence of Wheel Slip
… an initial position while the controller keeps minimizing offsets with respect to the reference path. To achieve the accuracy required in agriculture, this work utilizes offset models derived based on kinematic models, which take both lateral and longitudinal slips into account. A model …
-
Enhancing trustworthiness in federated learning for disease prediction
… training and combines it with an AUC-oriented min--max optimization strategy to reduce the performance degradation that often occurs under severe label imbalance. The second contribution is MDANN, a fairness-aware framework that mitigates bias from multiple sensitive attributes by combining …
-
Robust model predictive control and scheduling co-design for networked cyber-physical systems
… and the interpolating coefficient is determined via optimization at the time instants when the MPC-based control is triggered. The original constraints are properly tightened to achieve robust constraint optimization and a sequence of dynamic sets used to test events are derived according …
-
Stochastic Optimization for Structured Problems with Applications in Machine Learning
Structured optimization problems arise in various machine learning applications, including hyperparameter tuning, NDCG (Normalized Discounted Cumulative Gain) optimization, and AUC (area under the ROC curve) maximization, etc. These problems often involve complex structures, e.g. compositional, …
Page 1 of 2