Detecting emotional situations using convolutional neural networks and distributed models of human brain activity Emotions are thought to be canonical responses to situations ancestrally linked to survival or the well-being of an organism. Although sensory elements do not fully determine the nature of emotional responses, they should be sufficient to...
Osman Malik - Fast Randomized Matrix and Tensor Interpolative Decomposition Using CountSketch In this talk I will present our recently developed fast randomized algorithm for matrix interpolative decomposition. If time permits, I will also say a few words about how our method can be applied to the tensor interpolative decomposition...
"Don't go with the flow -- – A new tensor algebra for Neural Networks" Multi-dimensional information often involves multi-dimensional correlations that may remain latent by virtue of traditional matrix-based learning algorithms. In this study, we propose a tensor neural network framework that offers an exciting new paradigm for supervised machine...
Induction of time inconsistency in optimal stopping problem Time inconsistency is a common phenomenon of optimal control and optimal stopping problems, especially in finance and economics. It says a player will change his optimal strategy over time. To deal with such problem, we usually search for some consistent plan (equilibrium)...
Colton Grainger, Department of Mathematics, University of Colorado Boulder On Characterizing the Capacity of Neural Networks using Algebraic Topology The learnability of different neural architectures can be characterized directly by computable measures of data complexity. In this paper, we reframe the problem of architecture selection as understanding how data determines...
Exploiting Low-Dimensional Structure in Optimization Under Uncertainty In computational science, optimization under uncertainty (OUU) provides a new methodology for building designs reliable under a variety of conditions with improved efficiency over a traditional, safety factor based approach. However, the resulting optimization problems can be challenging. For example, chance constraints bounding...
Fast Rates for Unbounded Losses: from ERM to Generalized Bayes I will present new excess risk bounds for randomized and deterministic estimators, discarding boundedness assumptions to handle general unbounded loss functions like log loss and squared loss under heavy tails. These bounds have a PAC-Bayesian flavor in both derivation and...
Fast Algorithms and Community Software for Physical Prediction, Inference, and Design Physically-based computational models are the foundation of modern science and engineering, providing the only path to reliable prediction and inference in the presence of sparse and indirect observations as well as deeper understanding of interacting physical processes and scales...
Online Optimization with Feedback The talk focuses on the design and analysis of running (i.e., online) algorithmic solutions to control systems or networked systems based on performance objectives and engineering constraints that may evolve over time. The time-varying convex optimization formalism is leveraged to model optimal operational trajectories of the...