Non-convex constrained optimization problems have become a powerful framework for modeling a wide range of machine learning problems, with applications in k-means clustering, large- scale semidefinite programs (SDPs), and various other tasks. As the perfor ...
The goal of this paper is to characterize function distributions that general neural networks trained by descent algorithms (GD/SGD), can or cannot learn in polytime. The results are: (1) The paradigm of general neural networks trained by SGD is poly-time ...
Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...
In this paper, we present a spatial branch and bound algorithm to tackle the continuous pricing problem, where demand is captured by an advanced discrete choice model (DCM). Advanced DCMs, like mixed logit or latent class models, are capable of modeling de ...
This work studies the power density (PD) optimization in wind farms, and its sensitivity to the available area size. A novel genetic algorithm (PDGA) is introduced, which optimizes PD and the turbine layout, by self-adapting to the PD and to the solutions ...
Control systems operating in real-world environments often face disturbances arising from measurement noise and model mismatch. These factors can significantly impact the perfor- mance and safety of the system. In this thesis, we aim to leverage data to de ...
The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins.
All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...
In this work we consider an online learning problem, called Online k-Clustering with Moving Costs, at which a learner maintains a set of k facilities over T rounds so as to minimize the connection cost of an adversarially selected sequence of clients. The ...
Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by early-stopped unconstrain ...
We apply inverse reinforcement learning (IRL) with a novel cost feature to the problem of robot navigation in human crowds. Consistent with prior empirical work on pedestrian behavior, the feature anticipates collisions between agents. We efficiently learn ...
