Explore the latest research from Facebook
Filter by
Research Area
- All
- Academic Programs
- AR/VR
- Artificial Intelligence
- Blockchain & Cryptoeconomics
- Computational Photography & Intelligent Cameras
- Computer Vision
- Data Science
- Databases
- Economics & Computation
- Human Computer Interaction & UX
- Machine Learning
- Natural Language Processing & Speech
- Networking & Connectivity
- Security & Privacy
- Systems & Infrastructure
All Publications
Meta Learning via Learned Loss
In this paper, we take the first step towards automating this process, with the view of producing models which train faster and more robustly. Concretely, we present a meta-learning method for learning parametric loss functions that can generalize across different tasks and model architectures.
Paper
IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RL
We propose a novel framework to identify subgoals useful for exploration in sequential decision making tasks under partial observability.
Paper
Asynchronous Gradient-Push
We consider a multi-agent framework for distributed optimization where each agent has access to a local smooth strongly convex function, and the collective goal is to achieve consensus on the parameters that minimize the sum of the agents’ local functions. We propose an algorithm wherein each agent operates asynchronously and independently of the other agents.
Paper
Contact Burn Injuries Part I: The influence of object thermal mass
This paper is the first of a two-part series that discusses a numerical methodology that relies on the concept of cumulative equivalent exposure to evaluate contact burn injury thresholds.
Paper
Contact Burn Injuries Part II: The influence of object shape, size, contact resistance, and applied heat flux
This paper is the second of a two-part series that discusses a numerical methodology that relies on the concept of cumulative equivalent exposure to evaluate contact burn injury thresholds. In Part I, the effect of a finite thermal mass is analyzed for an infinite plate of several finite thicknesses. In Part II, the sensitivities to object shape, size, thickness, contact resistance and applied heat flux are considered.
Paper
Online Bayesian Persuasion
In Bayesian persuasion, an informed sender has to design a signaling scheme that discloses the right amount of information so as to influence the behavior of a self-interested receiver. This kind of strategic interaction is ubiquitous in real-world economic scenarios. However, the seminal model by Kamenica and Gentzkow makes some stringent assumptions that limit its applicability in practice.
Paper
Triple descent and the two kinds of overfitting: Where & why do they appear?
A recent line of research has highlighted the existence of a “double descent” phenomenon in deep learning, whereby increasing the number of training examples N causes the generalization error of neural networks to peak when N is of the same order as the number of parameters P. In earlier works, a similar phenomenon was shown to exist in simpler models such as linear regression, where the peak instead occurs when N is equal to the input dimension D. Since both peaks coincide with the interpolation threshold, they are often conflated in the literature. In this paper, we show that despite their apparent similarity, these two scenarios are inherently different.
Paper
Situated and Interactive Multimodal Conversations
Next generation virtual assistants are envisioned to handle multimodal inputs (e.g., vision, memories of previous interactions, and the user’s utterances), and perform multimodal actions (e.g., displaying a route while generating the system’s utterance). We introduce Situated Interactive MultiModal Conversations (SIMMC) as a new direction aimed at training agents that take multimodal actions grounded in a co-evolving multimodal input context in addition to the dialog history.
Paper
Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programming
Motivated by the needs of resource constrained dialog policy learning, we introduce dialog policy via differentiable inductive logic (DILOG). We explore the tasks of one-shot learning and zero-shot domain transfer with DILOG on SimDial and MultiWoZ.
Paper
Best Practices for Data-Efficient Modeling in NLG: How to Train Production-Ready Neural Models with Less Data
In this paper, we present approaches that have helped us deploy data-efficient neural solutions for NLG in conversational systems to production. We describe a family of sampling and modeling techniques to attain production quality with light-weight neural network models using only a fraction of the data that would be necessary otherwise, and show a thorough comparison between each.
Paper