## Schedule ### Sunday December 8

### Monday December 9

WORKSHOP
LatinX in AI
KEYNOTE: Carlos Guestrin - Systems Perspectives into Human-Centered Machine Learning

### Tuesday December 10

### Wednesday December 11

ACCEPTED PAPER
Multiple Futures Prediction

ACCEPTED PAPER
Data Parameters: A New Family of Parameters for Learning a Differentiable Curriculum

### Friday December 13

WORKSHOP
Machine Learning for Health (ML4H): What makes machine learning in medicine different?
KEYNOTE: Emily Fox (NeurIPS 2019 Program Co-Chair) - Models of Cognition: From Predicting Cognitive Impairment to the Brain Networks underlying Complex Cognitive Processes
PRESENTATION: Modeling patterns of smartphone usage and their relationship to cognitive health

WORKSHOP
Beyond First Order Methods in ML
PRESENTATION: Nonlinear Conjugate Gradients for Scaling Synchronous Distributed DNN Training

## Accepted Papers ### [Adversarial Fisher Vectors for Unsupervised Representation Learning](/research/adversarial-fisher-vectors-for-unsupervised-representation-learning) *Shuangfei Zhai, Walter Talbott, Carlos Guestrin, Joshua M. Susskind* We examine Generative Adversarial Networks (GANs) through the lens of deep Energy Based Models (EBMs), with the goal of exploiting the density model that follows from this formulation. In contrast to a traditional view where the discriminator learns a constant function when reaching convergence, here we show that it can provide useful information for downstream tasks, e.g., feature extraction for classification. To be concrete, in the EBM formulation, the discriminator learns an unnormalized density function (i.e., the negative energy term) that characterizes the data manifold. We propose to evaluate both the generator and the discriminator by deriving corresponding Fisher Score and Fisher Information from the EBM. We show that by assuming that the generated examples form an estimate of the learned density, both the Fisher Information and the normalized Fisher Vectors are easy to compute. We also show that we are able to derive a distance metric between examples and between sets of examples. We conduct experiments showing that the GAN-induced Fisher Vectors demonstrate competitive performance as unsupervised feature extractors for classification and perceptual similarity tasks. ### [Data Parameters: A New Family of Parameters for Learning a Differentiable Curriculum](/research/data-parameters) *Shreyas Saxena, Oncel Tuzel, Dennis DeCoste* Recent works have shown that learning from easier instances first can help deep neural networks (DNNs) generalize better. However, knowing which data to present during different stages of training is a challenging problem. In this work, we address this problem by introducing data parameters. More specifically, we equip each sample and class in a dataset with a learnable parameter (data parameters), which governs their importance in the learning process. During training, at each iteration, as we update the model parameters, we also update the data parameters. These updates are done by gradient descent and do not require hand-crafted rules or design. When applied to image classification task on CIFAR10, CIFAR100, WebVision and ImageNet datasets, and object detection task on KITTI dataset, learning a dynamic curriculum via data parameters leads to consistent gains, without any increase in model complexity or training time. When applied to a noisy dataset, the proposed method learns to learn from clean images and improves over the state-of-the-art methods by 14%. To the best of our knowledge, our work is the first curriculum learning method to show gains on large scale image classification and detection tasks. ### [Multiple Futures Prediction](/research/multiple-futures-prediction) *Yichuan Charlie Tang, Ruslan Salakhutdinov* Temporal prediction is critical for making intelligent and robust decisions in complex dynamic environments. Motion prediction needs to model the inherently uncertain future which often contains multiple potential outcomes, due to multi-agent interactions and the latent goals of others. Towards these goals, we introduce a probabilistic framework that efficiently learns latent variables to jointly model the multi-step future motions of agents in a scene. Our framework is data-driven and learns semantically meaningful latent variables to represent the multimodal future, without requiring explicit labels. Using a dynamic attention-based state encoder, we learn to encode the past as well as the future interactions among agents, efficiently scaling to any number of agents. Finally, our model can be used for planning via computing a conditional probability density over the trajectories of other agents given a hypothetical rollout of the ‘self’ agent. We demonstrate our algorithms by predicting vehicle trajectories of both simulated and real data, demonstrating the state-of-the-art results on several vehicle trajectory datasets.

Updates and events.

Discover opportunities in Machine Learning.