Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions. It is well known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and well-chosen training parameters (batch size, learning rate, optimizer) produce minimizers that generalize better. However, the reasons for these differences, and their effect on the underlying loss landscape, is not well understood. In this paper, we explore the structure of neural loss functions, and the effect of loss landscapes on generalization, using a range of visualization methods. First, we introduce a simple "filter normalization" method that helps us visualize loss function curvature, and make meaningful side-by-side comp arisons between loss functions. Then, using a variety of visualizations, we explore how network architecture affects the loss landscape, and how training parameters affect the shape of minimizers.

Variance reduction (VR) methods boost the performance of stochastic gradient descent (SGD) by enabling the use of larger, constant stepsizes and preserving linear convergence rates. However, current variance reduced SGD methods require either high memory usage or an exact gradient computation (using the entire dataset) at the end of each epoch. This limits the use of VR methods in practical distributed settings. In this paper, we propose a variance reduction method, called VR-lite, that does not require full gradient computations or extra storage. We explore distributed synchronous and asynchronous variants that are scalable and remain stable with low communication frequency. We empirically compare both the sequential and distributed algorithms to state-of-the-art stochastic optimization methods, and find that our proposed algorithms perform favorably to other stochastic methods.

As datasets for machine learning grow larger, parallelization strategies become more and more important. Recent approaches to distributed modelfitting rely heavily either on consensus ADMM, where each node solves smallsub-problems using only local data, or on stochastic gradient methods thatdon't scale well to large numbers of cores in a cluster setting. For this reason, GPU clusters have become common prerequisites to large-scale machinelearning. This paper describes an unconventional training method that uses alternating direction methods and Bregman iteration to train a variety of machine learning models on CPUs while avoiding the drawbacks of consensus methods and without gradient descent steps. Using transpose reduction strategies, the proposed method reduces the optimization problems to a sequence of minimization sub-steps that can each be solved globally in closed form. The method provides strong scaling in the distributed setting, yielding linear speedups even when split over thousands of cores.

However, foundational problems remain in the either mindfully or inadvertently by individuals or teams of continuing development of AI for team autonomy, humans. One worry about this bright future is that jobs especially with objective measures able to optimize team may be lost; from Mims (2015), function, performance and composition. Something potentially momentous is happening inside AI approaches often attempt to address autonomy by startups, and it's a practice that many of their established modeling aspects of human decision-making or behavior.

The AAAI 2015 Spring Symposium Series was held Monday through Wednesday, March 23-25, at Stanford University near Palo Alto, California. The titles of the seven symposia were Ambient Intelligence for Health and Cognitive Enhancement, Applied Computational Game Theory, Foundations of Autonomy and Its (Cyber) Threats: From Individuals to Interdependence, Knowledge Representation and Reasoning: Integrating Symbolic and Neural Approaches, Logical Formalizations of Commonsense Reasoning, Socio-Technical Behavior Mining: From Data to Decisions, Structured Data for Humanitarian Technologies: Perfect Fit or Overkill?

The AAAI 2015 Spring Symposium Series was held Monday through Wednesday, March 23-25, at Stanford University near Palo Alto, California. The titles of the seven symposia were Ambient Intelligence for Health and Cognitive Enhancement, Applied Computational Game Theory, Foundations of Autonomy and Its (Cyber) Threats: From Individuals to Interdependence, Knowledge Representation and Reasoning: Integrating Symbolic and Neural Approaches, Logical Formalizations of Commonsense Reasoning, Socio-Technical Behavior Mining: From Data to Decisions, Structured Data for Humanitarian Technologies: Perfect Fit or Overkill? and Turn-Taking and Coordination in Human-Machine Interaction.The highlights of each symposium are presented in this report.

Recently, Petrik et al. demonstrated that L1Regularized Approximate Linear Programming (RALP) could produce value functions and policies which compared favorably to established linear value function approximation techniques like LSPI. RALP's success primarily stems from the ability to solve the feature selection and value function approximation steps simultaneously. RALP's performance guarantees become looser if sampled next states are used. For very noisy domains, RALP requires an accurate model rather than samples, which can be unrealistic in some practical scenarios. In this paper, we demonstrate this weakness, and then introduce Locally Smoothed L1-Regularized Approximate Linear Programming (LS-RALP). We demonstrate that LS-RALP mitigates inaccuracies stemming from noise even without an accurate model. We show that, given some smoothness assumptions, as the number of samples increases, error from noise approaches zero, and provide experimental examples of LS-RALP's success on common reinforcement learning benchmark problems.

Approximate dynamic programming has been used successfully in a large variety of domains, but it relies on a small set of provided approximation features to calculate solutions reliably. Large and rich sets of features can cause existing algorithms to overfit because of a limited number of samples. We address this shortcoming using $L_1$ regularization in approximate linear programming. Because the proposed method can automatically select the appropriate richness of features, its performance does not degrade with an increasing number of features. These results rely on new and stronger sampling bounds for regularized approximate linear programs. We also propose a computationally efficient homotopy method. The empirical evaluation of the approach shows that the proposed method performs well on simple MDPs and standard benchmark problems.