Home      Discussions      About
Join us

@cs.cmu.edu

Nov 19, 2018
By yuexinw
Computation and Language
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computation

Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Ta…

Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm e…
Nov 20, 2018
By katef
Robotics
Artificial Intelligence
Machine Learning

Model Learning for Look-ahead Exploration in Continuous Control

We propose an exploration method that incorporates look-ahead search over basic learnt skills and their dynamics, and use it for reinforcement learni…
Nov 23, 2018
Computation and Language
Artificial Intelligence

Words Can Shift: Dynamically Adjusting Word Representations Using N…

Humans convey their intentions through the usage of both verbal and nonverbal behaviors during face-to-face communication. Speaker intentions often v…
Feb 07, 2017
By xinleic
Computer Vision

 

An Implementation of Faster RCNN with Study for Region Sampling

We adapted the join-training scheme of Faster RCNN framework from Caffe to TensorFlow as a baseline implementation for object detection. Our code is …
Jan 12, 2019
By soheil
Data Structures and Algorithms
Distributed
Parallel
and Cluster Computing

We now prove Lemma 3.1, showing that Algorithm 3 can be used to reduce the overall graph degree. There are two parts to doing this. First, we need to amplify the success probability of Lemma 3.2, which only showed a degree reduction in expectation, …

Exponentially Faster Massively Parallel Maximal Matching

The study of graph problems in the Massively Parallel Computations (MPC) model has recently seen a burst of breakthroughs. Czumaj et al. [STOC'18], A…
Jan 29, 2019
Computation and Language

No Training Required: Exploring Random Encoders for Sentence Classi…

We explore various methods for computing sentence representations from pre-trained word embeddings without any training, i.e., using nothing but rand…
Jul 12, 2012
By aramdas
Machine Learning

We focus on the problem of minimizing a convex function $f$ over a convex set $S$ given $T$ queries to a stochastic first order oracle. We argue that the complexity of convex minimization is only determined by the rate of growth of the function arou…

Optimal rates for first-order stochastic convex optimization under …

We focus on the problem of minimizing a convex function $f$ over a convex set $S$ given $T$ queries to a stochastic first order oracle. We argue that…
Jan 06, 2019
By xuezhem
Machine Learning
Computer Vision

MAE: Mutual Posterior-Divergence Regularization for Variational Aut…

Variational Autoencoder (VAE), a simple and effective deep generative model, has led to a number of impressive empirical successes and spawned many a…
Jan 12, 2019
Computation and Language

EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning i…

Quantitative reasoning is an important component of reasoning that any intelligent natural language understanding system can reasonably be expected t…
Mar 15, 2016
By ehovy
Computation and Language
Machine Learning

Coreference resolution is one of the first stages in deep language understanding and its importance has been well recognized in the natural language processing community. In this paper, we propose a generative, unsupervised ranking model for entity …

Unsupervised Ranking Model for Entity Coreference Resolution

Coreference resolution is one of the first stages in deep language understanding and its importance has been well recognized in the natural language …
Oct 07, 2018
By ckroer
Computer Science and Game Theory
Artificial Intelligence

We introduced a practical variant of the EGT algorithm that employs aggressive stepsizes, μ balancing, a numerically-friendly smoothed-best-response algorithm, parallelization via Cartesian product operations at the root of the strategy treeplex, an…

Solving Large Sequential Games with the Excessive Gap Technique

There has been tremendous recent progress on equilibrium-finding algorithms for zero-sum imperfect-information extensive-form games, but there has be…
May 23, 2016
By hongyiz
Optimization and Control
Machine Learning

Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds

We study optimization of finite sums of geodesically smooth functions on Riemannian manifolds. Although variance reduction techniques for optimizing …
Nov 01, 2018
Information Retrieval
Machine Learning

Online Diverse Learning to Rank from Partial-Click Feedback

Learning to rank is an important problem in machine learning and recommender systems. In a recommender system, a user is typically recommended a list…
Nov 03, 2018
By anindya
Machine Learning
Computational Complexity
Data Structures and Algorithms

Learning sparse mixtures of rankings from noisy information

We study the problem of learning an unknown mixture of $k$ rankings over $n$ elements, given access to noisy samples drawn from the unknown mixture. …
Nov 01, 2018
Machine Learning
Artificial Intelligence

We propose a framework for learning beam search policies using imitation learning. We provide regret guarantees for both new and existing algorithms for learning beam search policies. One of the main contributions is formulating learning beam search…

Learning Beam Search Policies via Imitation Learning

Beam search is widely used for approximate decoding in structured prediction problems. Models often use a beam at test time but ignore its existence …
Nov 06, 2018
Machine Learning

Double Adaptive Stochastic Gradient Optimization

Adaptive moment methods have been remarkably successful in deep learning optimization, particularly in the presence of noisy and/or sparse gradients.…
Nov 10, 2018
Computation and Language

Zero-shot Neural Transfer for Cross-lingual Entity Linking

Cross-lingual entity linking maps an entity mention in a source language to its corresponding entry in a structured knowledge base that is in a diffe…
Oct 18, 2018
By ninamf
Data Structures and Algorithms
Machine Learning

Testing Matrix Rank, Optimally

We show that for the problem of testing if a matrix $A \in F^{n \times n}$ has rank at most $d$, or requires changing an $\epsilon$-fraction of entri…
Jun 09, 2015
Machine Learning

On the Error of Random Fourier Features

Kernel methods give powerful, flexible, and theoretically grounded approaches to solving many problems in machine learning. The standard approach, ho…
Jun 13, 2014
By danai
Social and Information Networks
Physics and Society

VoG: Summarizing and Understanding Large Graphs

How can we succinctly describe a million-node graph with a few simple sentences? How can we measure the "importance" of a set of discovered subgraphs…
There aren't more papers

Request Comment

or Invite via email
You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test
Test description