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 12 of 12 for “"Frank-Wolfe method"”.
-
Momentum for the Frank Wolfe Method
… sparse) solutions. Conditional gradient, aka Frank Wolfe (FW) algorithms, have well-documented merits in machine learning and signal processing applications that involves minimizing a loss function with constraints. Compared to projection based methods, one of the key benefits is that FW …
-
Understanding Modern Techniques in Optimization: Frank-Wolfe, Nesterov's Momentum, and Polyak's Momentum
… algorithms, the popular ones include the Frank-Wolfe method, Nesterov's accelerated methods, and Polyak's momentum. While theoretical analysis of the Frank-Wolfe method and Nesterov's methods are available in the literature, the analysis can be quite complicated or less intuitive. Polyak's …
-
Integrating Congestion Pricing And Transit Investment Planning
… is an integration of a genetic algorithm and the Frank-Wolfe method. The method and solution procedure is applied to an illustrative example.
-
Investigation and implementation of an algorithm for computing optimal search paths
… N x T network. Lower bounds are obtained via the Frank-Wolfe method of solution specialized for acyclic networks. This technique relies on linearization of the objective function to yield a shortest path problem that is solvable by dynamic programming. For each iteration, the lower bound can be …
-
Wasserstein Adversarial Robustness
… projected gradient attack; (b) we show that the Frank-Wolfe method equipped with a suitable linear minimization oracle works extremely fast under Wasserstein constraints. Our algorithms not only converge faster but also generate much stronger attacks. For instance, we decrease the accuracy of a …
-
Implementable algorithms for stochastic nonlinear programs with applications to portfolio selection and revision
… problems, and second, to apply these methods to the solution of portfolio selection and revision problems. The algorithms developed are based upon the Frank-Wolfe method. A convergent algorithm is developed which modifies this approach to allow for sequences of approximations to the …
-
Data-driven design for multihop and multi-band cellular networks
… develop an optimization algorithm based on the Frank-Wolfe method. The MPC approach improves the 5th percentile service rate by 2.7x compared to the traditional signal strength-based association. Its performance approaches that of a genie-aided scheme in terms of the number of handovers.
-
Scalable Optimization Methods for Machine Learning: Structures, Properties and Applications
… performance limits on traditional state-of-art methods. In this thesis, we conduct a systematic study on scalable optimization methods. Our investigations mainly cover three aspects: the role of special structures in the models, convergence properties of algorithms, and applications in machine …
-
Estimation and Enhancement of Tissue Motion Using Ultrasound Imaging
… We propose a novel ultrasound elastography method where unlike conventional techniques, three ultrasound RF frames are taken into account to devise a cost function consisting of data term, spatial regularization terms and temporal continuity prior. We find the strain map by taking the …
-
Optimal stochastic and distributed algorithms for machine learning
… the averaged SGD. The Alternating Direction Method of Multipliers (ADMM) is another flexible method to explore function structures. In the second part we proposed stochastic ADMM that can be applied to a general class of convex and nonsmooth functions, beyond the smooth and separable least …
-
A reduction framework for approximate extended formulations and a faster algorithm for convex optimization
… gradient type algorithms (also known as Frank-Wolfe type methods) are very important in theory as well as in practice due to their simplicity and fast convergence. We show how we can eliminate the linear optimization step performed in every iteration of Frank-Wolfe type methods and …
-
Συντονισμός και ανταγωνισμός στην εφοδιαστική αλυσίδα: προσεγγίσεις βελτιστοποίησης και θεωρίας παιγνίων
… κατεύθυνσης που στηρίζεται στην γνωστή μέθοδο Frank-Wolfe. Αναπτύσσουμε επίσης παιγνιοθεωρητικές ερμηνείες για κάποιες μορφές της μεθόδου. Οι επιπτώσεις που έχει ο ανταγωνισμός στην εξασφάλιση του επιθυμητού επιπέδου υπηρεσιών στην χωροθέτηση των κέντρων διανομής και τη κατανομή δυναμικότητας …