Skip to footer

Results for Artificial Intelligence / Machine Learning

First-Order Preconditioning via Hypergradient Descent

T. Moskovitz, R. Wang, J. Lan, S. Kapoor, T. Miconi, J. Yosinski, A. Rawal
Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space.These difficulties can be addressed by second-order approaches that apply a pre-conditioning matrix to the gradient to improve convergence. Unfortunately, such algorithms typically struggle to scale to high-dimensional problems, in part because the calculation of specific preconditioners such as the inverse Hessian or Fisher information matrix is highly expensive. We introduce first-order preconditioning (FOP), a fast, scalable approach that generalizes previous work on hypergradient descent (Almeida et al., 1998; Maclaurin et al., 2015; Baydin et al.,2017) to learn a preconditioning matrix that only makes use of first-order information.
[…] [PDF]
Conference on Neural Information Processing Systems (NeurlPS), 2019

Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based Methods

J. Zhi, R. Wang, J. Clune, K. Stanley
Recent advances in machine learning are consistently enabled by increasing amounts of computation. Reinforcement learning (RL) and population-based methods in particular pose unique challenges for efficiency and flexibility to the underlying distributed computing frameworks. These challenges include frequent interaction with simulations, the need for dynamic scaling, and the need for a user interface with low adoption cost and consistency across different backends. In this paper we address these challenges while still retaining development efficiency and flexibility for both research and practical applications by introducing Fiber, a scalable distributed computing framework for RL and population-based methods. […] [PDF]

Estimating Q(s,s’) with Deep Deterministic Dynamics Gradients

A. Edwards, Himanshu Sahni, R. Liu, J. Hung, A. Jain, R. Wang, A. Ecoffet, T. Miconi, C. Isbell, J. Yosinski
In this paper, we introduce a novel form of value function, Q(s,s′), that expresses the utility of transitioning from a state s to a neighboring state s′ and then acting optimally thereafter. In order to derive an optimal policy, we develop a forward dynamics model that learns to make next-state predictions that maximize this value. […] [PDF]
International Conference on Machine Learning (ICML), 2020

Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions

R. Wang, J. Lehman, A. Rawal, J. Zhi, Y. Li, J. Clune, K. Stanley
Creating open-ended algorithms, which generate their own never-ending stream of novel and appropriately challenging learning opportunities, could help to automate and accelerate progress in machine learning. A recent step in this direction is the Paired Open-Ended Trailblazer (POET), an algorithm that generates and solves its own challenges, and allows solutions to goal-switch between challenges to avoid local optima. Here we introduce and empirically validate two new innovations to the original algorithm, as well as two external innovations designed to help elucidate its full potential. […] [PDF]
International Conference on Machine Learning (ICML), 2020

Heterogeneous Causal Learning for Effectiveness Optimization in User Marketing

W. Y. Zou, S. Du, J. Lee, J. Pedersen
User marketing is a key focus of consumer-based internet companies. Learning algorithms are effective to optimize marketing campaigns which increase user engagement, and facilitates cross-marketing to related products. By attracting users with rewards, marketing methods are effective to boost user activity in the desired products. Rewards incur significant cost that can be off-set by increase in future revenue. […] [PDF]

Learning Continuous Treatment Policy and Bipartite Embeddings for Matching with Heterogeneous Causal Effects

W. Y. Zou, S. Shyam, M. Mui, M. Wang, J. Pedersen, Z. Ghahramani

Causal inference methods are widely applied in the fields of medicine, policy, and economics. Central to these applications is the estimation of treatment effects to make decisions. Current methods make binary yes-or-no decisions based on the treatment effect of a single outcome dimension. These methods are unable to capture continuous space treatment policies with a measure of intensity. […] [PDF]

Plug and Play Language Models: A Simple Approach to Controlled Text Generation

S. Dathathri, A. Madotto, J. Lan, J. Hung, E. Frank, P. Molino, J. Yosinski, R. Liu
Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities. However, controlling attributes of the generated language (e.g. switching topic or sentiment) is difficult without modifying the model architecture or fine-tuning on attribute-specific data and entailing the significant cost of retraining. We propose a simple alternative: the Plug and Play Language Model (PPLM) for controllable language generation, which combines a pretrained LM with one or more simple attribute classifiers that guide text generation without any further training of the LM. [PDF]
International Conference on Learning Representations (ICLR), 2020

Joint Interaction and Trajectory Prediction for Autonomous Driving using Graph Neural Networks

D. Lee, Y. Gu, J. Hoang, M. Marchetti-Bowick
Using weakly intent label can potentially predict the interaction and the resulting trajectory better. We use a GNN to model the interaction. [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019

Identifying Unknown Instances for Autonomous Driving

K. Wong, S. Wang, M. Ren, M. Liang, R. Urtasun
We propose a novel open-set instance segmentation algorithm for point clouds that identifies instances from both known and unknown classes. In particular, we train a deep convolutional neural network that projects points belonging to the same instance together in a category-agnostic embedding space. [PDF]
The Conference on Robot Learning (CoRL), 2019

Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction

A. Jain, S. Casas, R. Liao, Y. Xiong, S. Feng, S. Segal, R. Urtasun
Our research shows that non-parametric distributions can capture extremely well the (erratic) pedestrian behavior. We propose Discrete Residual Flow, a convolutional neural network for human motion prediction that accurately models the temporal dependencies and captures the uncertainty inherent in long-range motion forecasting. In particular, our method captures multi-modal posteriors over future human motion very realistically. [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019

Incremental Few-Shot Learning with Attention Attractor Networks

M. Ren, R. Liao, E. Fetaya, R. Zemel
This paper addresses this problem, incremental few- shot learning, where a regular classification network has already been trained to recognize a set of base classes, and several extra novel classes are being considered, each with only a few labeled examples. After learning the novel classes, the model is then evaluated on the overall classification performance on both base and novel classes. To this end, we propose a meta-learning model, the Attention Attractor Networks, which regularizes the learning of novel classes. [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019

Efficient Graph Generation with Graph Recurrent Attention Networks

R. Liao, Y. Li, Y. Song, S. Wang, C. Nash, W. L. Hamilton, . Duvenaud, R. Urtasun, R.S. Zemel
We propose a new family of efficient and expressive generative models of graphs, called Graph Recurrent Attention Networks (GRANs). On standard benchmarks, our model generates graphs comparable in quality with the previous state-of-the-art, and is at least an order of magnitude faster. [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019

Learning Joint 2D-3D Representations for Depth Completion

Y. Chen, B. Yang, M. Liang, R. Urtasun
We design a simple yet effective architecture that fuses information between 2D and 3D representations at multiple levels to learn fully fused joint representations at multiple levels, and show state-of-the-art results on the KITTI depth completion benchmark. [PDF]
International Conference on Computer Vision (ICCV), 2019

Improving Movement Prediction of Traffic Actors using Off-road Loss and Bias Mitigation

M. Niedoba, H. Cui, K. Luo, D. Hegde, F.-C. Chou, N. Djuric
In this work improves the predictions for traffic actor with two novel methods: off-road losses and action category upweighting. The off-road losses compliment the traditional L2 distance loss by penalizing the unrealistic off-road predictions. [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019

DAGMapper: Learning to Map by Discovering Lane Topology

N. Homayounfar, W.-C. Ma\*, J. Liang\*, X. Wu, J. Fan, R. Urtasun
We map complex lane topologies in highways by formulating the problem as a deep directed graphical model. As an interesting result, we can train our model in I40 and generalize to unseen highways in SF. [PDF]
International Conference on Computer Vision (ICCV), 2019

DMM-Net: Differentiable Mask-Matching Network for Video Instance Segmentation

X. Zeng, R. Liao, L. Gu, Y. Xiong, S. Fidler, R. Urtasun
We propose the differentiable mask-matching network (DMM-Net) for solving the video instance segmentation problem where the initial instance masks are provided. On DAVIS 2017 dataset, DMM-Net achieves the best performance without online learning on the first frames and the 2nd best with it. Without any fine-tuning, DMM-Net performs comparably to state-of-the-art methods on SegTrack v2 dataset. [PDF]
International Conference on Computer Vision (ICCV), 2019

Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving

N. Djuric, V. Radosavljevic, H. Cui, T. Nguyen, F.-C. Chou, T.-H. Lin, N. Singh, J. Schneider
We introduce an approach that takes into account a current world state and produces rasterized representations of each traffic actor’s vicinity. The raster images are then used as inputs to deep convnets to infer future movement of actors while also accounting for and capturing inherent uncertainty of the prediction task, with extensive experiments on real-world data strongly suggest benefits of the proposed approach. [PDF]
Winter Conference on Applications of Computer Vision (WACV), 2020

Hamiltonian Neural Networks

S. Greydanus, M. Dzamba, J. Yosinski
Even though neural networks enjoy widespread use, they still struggle to learn the basic laws of physics. How might we endow them with better inductive biases? In this paper, we draw inspiration from Hamiltonian mechanics to train models that learn and respect exact conservation laws in an unsupervised manner. […] [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019

LCA: Loss Change Allocation for Neural Network Training

J. Lan, R. Liu, H. Zhou, J. Yosinski
Neural networks enjoy widespread use, but many aspects of their training, representation, and operation are poorly understood. In particular, our view into the training process is limited, with a single scalar loss being the most common viewport into this high-dimensional, dynamic process. We propose a new window into training called Loss Change Allocation (LCA), in which credit for changes to the network loss is conservatively partitioned to the parameters. […] [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019

Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask

H. Zhou, J. Lan, R. Liu, J. Yosinski
Optical Character Recognition (OCR) approaches have been widely advanced in recent years thanks to the resurgence of deep learning. The state-of-the-art models are mainly trained on the datasets consisting of the constrained scenes. Detecting and recognizing text from the real-world images remains a technical challenge. […] [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019

DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch

S. Duggal, S. Wang, W.-C. Ma, R. Hu, R. Urtasun
We propose a real-time dense depth estimation approach using stereo image pairs, which utilizes differentiable Patch Match to progressively prune the stereo matching search space. Our model achieves competitive performance on the KITTI benchmark despite running in real time. [PDF]
International Conference on Computer Vision (ICCV), 2019

Maximum Relevance and Minimum Redundancy Feature Selection Methods for a Marketing Machine Learning Platform

Z. Zhao, R. Anand, M. Wang
In machine learning applications for online product offerings and marketing strategies, there are often hundreds or thousands of features available to build such models. Feature selection is one essential method in such applications for multiple objectives: improving the prediction accuracy by eliminating irrelevant features, accelerating the model training and prediction speed, reducing the monitoring and maintenance workload for feature data pipeline, and providing better model interpretation and diagnosis capability. […] [PDF]
IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2019

Uplift Modeling for Multiple Treatments with Cost Optimization

Z. Zhao, T. Harinen
Uplift modeling is an emerging machine learning approach for estimating the treatment effect at an individual or subgroup level. It can be used for optimizing the performance of interventions such as marketing campaigns and product designs. […] [PDF]
IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2019

DSIC: Deep Stereo Image Compression

J. Liu, S. Wang, R. Urtasun
We design a novel architecture for compressing a stereo image pair that tries to extract as much shared information from the first image in order to reduce the bitrate of the second image. We demonstrate an impressive 30-50% reduction in the second image bitrate at low bitrates. [PDF]
International Conference on Computer Vision (ICCV), 2019

Flexibly-Structured Model for Task-Oriented Dialogues

L. Shu, P. Molino, M. Namazifar, H. Xu, B. Liu, H. Zheng, G. Tur
This paper proposes a novel end-to-end architecture for task-oriented dialogue systems. It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are modeled jointly with a structured copy-augmented sequential decoder and a multi-label decoder for each slot. The policy engine and language generation tasks are modeled jointly following that. […] [PDF]

Improve User Retention with Causal Learning

S. Du, J. Lee, F. Ghaffarizadeh
User retention is a key focus for consumer based internet companies and promotions are an effective lever to improve retention. However, companies rely either on non-causal churn prediction to capture heterogeneity or on regular A/B testing to capture average treatment effect. In this paper, we propose a heterogeneous treatment effect optimization framework to capture both heterogeneity and causal effect. […] [PDF]
SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2019

Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints

M. Li, E. Yumer, D. Ramanan
Current approaches for hyper-parameter tuning and neural architecture search tend to be limited by practical resource constraints. Therefore, we introduce a formal setting for studying training under the non-asymptotic, resource-constrained regime, i.e. budgeted training. We analyze the following problem: “given a dataset, algorithm, and resource budget, what is the best achievable performance?” [PDF]
International Conference on Learning Representations (ICLR), 2020

Evolvability ES: Scalable and Direct Optimization of Evolvability

A. Gajewski, J. Clune, K. O. Stanley, J. Lehman
Designing evolutionary algorithms capable of uncovering highly evolvable representations is an open challenge; such evolvability is important because it accelerates evolution and enables fast adaptation to changing circumstances. This paper introduces evolvability ES, an evolutionary algorithm designed to explicitly and efficiently optimize for evolvability, i.e. the ability to further adapt. […] [PDF]
The Genetic and Evolutionary Computation Conference (GECCO), 2019

Probabilistic Programming for Birth-Death Models of Evolution Using an Alive Particle Filter with Delayed Sampling

J. Kudlicka, L. M. Murray, F. Ronquist, T. B. Schön
We consider probabilistic programming for birth-death models of evolution and introduce a new widely-applicable inference method that combines an extension of the alive particle filter (APF) with automatic Rao-Blackwellization via delayed sampling. […] [PDF]
Conference on Uncertainty in Artificial Intelligence (UAI), 2019

Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning

A. Papangelis, Y.-C. Wang, P. Molino, G. Tur
We present the first complete attempt at concurrently training conversational agents that communicate only via self-generated language. Using DSTC2 as seed data, we trained natural language understanding (NLU) and generation (NLG) networks for each agent and let the agents interact online. […] [PDF]
Special Interest Group on Discourse and Dialogue (SIGDIAL), 2019

Page 1 of 6