Home      Discussions      About
Join us

@us.ibm.com

May 07, 2008
Combinatorics
Computational Complexity
Discrete Mathematics
Optimization and Control

This research was supported by the Mathematisches Forschungsinstitut Oberwolfach during a stay within the Research in Pairs Programme.

Nonlinear Optimization over a Weighted Independence System

We consider the problem of optimizing a nonlinear objective function over a weighted independence system presented by a linear-optimization oracle. W…
Oct 18, 2010
Machine Learning

We have established two hardness results for proper agnostic learning of low-degree PTFs. Our results show that even if there exist low-degree PTFs that are almost perfect hypotheses, it is computationally hard to find low-degree PTF hypotheses that…

Hardness Results for Agnostically Learning Low-Degree Polynomial Th…

Hardness results for maximum agreement problems have close connections to hardness results for proper learning in computational learning theory. In t…
Sep 26, 2011
Machine Learning
Data Structures and Algorithms

Christos Boutsidis acknowledges the support from XDATA program of the Defense Advanced Research Projects Agency (DARPA), administered through Air Force Research Laboratory contract FA8750-12-C-0323.

Deterministic Feature Selection for $k$-means Clustering

We study feature selection for $k$-means clustering. Although the literature contains many methods with good empirical performance, algorithms with p…
Mar 22, 2015
Distributed
Parallel
and Cluster Computing
Machine Learning

To summarize, our simple and robust cost model allows the costing of generated runtime plans for ML programs. This model automatically reflects all optimization decisions of the entire compilation chain. Most importantly it provides an analytical co…

Costing Generated Runtime Execution Plans for Large-Scale Machine L…

Declarative large-scale machine learning (ML) aims at the specification of ML algorithms in a high-level language and automatic generation of hybrid …
May 30, 2014
Data Structures and Algorithms
Machine Learning
Numerical Analysis

David Woodruff would like to thank the Simons Institute at Berkeley where part of this work was done. He would also like to acknowledge the XDATA program of the Defense Advanced Research Projects Agency (DARPA), administered through Air Force Resear…

Optimal CUR Matrix Decompositions

The CUR decomposition of an $m \times n$ matrix $A$ finds an $m \times c$ matrix $C$ with a subset of $c < n$ columns of $A,$ together with an $r \ti…
Jul 12, 2017
Conferences: ICML
Artificial Intelligence

A Formal Framework to Characterize Interpretability of Procedures

We provide a novel notion of what it means to be interpretable, looking past the usual association with human understanding. Our key insight is that …
Jul 05, 2016
Computation
Machine Learning

Efficient Estimation in the Tails of Gaussian Copulas

We consider the question of efficient estimation in the tails of Gaussian copulas. Our special focus is estimating expectations over multi-dimensiona…
Jan 22, 2015
Computation and Language
Machine Learning

Deep Multimodal Learning for Audio-Visual Speech Recognition

In this paper, we present methods in deep multimodal learning for fusing speech and visual modalities for Audio-Visual Automatic Speech Recognition (…
Apr 26, 2019
Machine Learning
Human-Computer Interaction

DPVis: Visual Exploration of Disease Progression Pathways

Clinical researchers use disease progression modeling algorithms to predict future patient status and characterize progression patterns. One approach…
Feb 10, 2019
Data Structures and Algorithms
Machine Learning

Scalable Fair Clustering

We study the fair variant of the classic $k$-median problem introduced by Chierichetti et al. [2017]. In the standard $k$-median problem, given an in…
Dec 11, 2017
Artificial Intelligence

This paper presents a novel algorithm termed eigenoption-critic (EOC) for hierarchical reinforcement learning. EOC extends the option-critic (OC) method by augmenting the extrinsic reward signals with eigenpurposes, intrinsic rewards defined by eige…

The Eigenoption-Critic Framework

Eigenoptions (EOs) have been recently introduced as a promising idea for generating a diverse set of options through the graph Laplacian, having been…
Jul 02, 2015
Data Structures and Algorithms

Approximation Algorithms for Connected Maximum Cut and Related Proble…

An instance of the Connected Maximum Cut problem consists of an undirected graph G = (V, E) and the goal is to find a subset of vertices S $\subseteq…
Jan 25, 2017
Information Theory

Hypothesis Testing under Maximal Leakage Privacy Constraints

The problem of publishing privacy-guaranteed data for hypothesis testing is studied using the maximal leakage (ML) as a metric for privacy and the ty…
Feb 17, 2016
Data Structures and Algorithms
Distributed
Parallel
and Cluster Computing

Work-Efficient Parallel and Incremental Graph Connectivity

On an evolving graph that is continuously updated by a high-velocity stream of edges, how can one efficiently maintain if two vertices are connected?…
Aug 25, 2014
Machine Learning

Improved Distributed Principal Component Analysis

We study the distributed computing setting in which there are multiple servers, each holding a set of points, who wish to compute functions on the un…
Apr 17, 2019
Computation and Language
Artificial Intelligence

Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and…

Conventional automatic speech recognition (ASR) systems trained from frame-level alignments can easily leverage posterior fusion to improve ASR accur…
Nov 09, 2012
Databases
Artificial Intelligence

MaTrust: An Effective Multi-Aspect Trust Inference Model

Trust is a fundamental concept in many real-world applications such as e-commerce and peer-to-peer networks. In these applications, users can generat…
Jun 12, 2016
Computer Vision

A constrained clustering based approach for matching a collection of …

In this paper, we consider the problem of finding the feature correspondences among a collection of feature sets, by using their point-wise unary fea…
May 19, 2018
Signal Processing
Artificial Intelligence

Designing communication systems via iterative improvement: error co…

In error correction coding (ECC), the typical error metric is the bit error rate (BER) which measures the number of bit errors. For this metric, the …
May 25, 2018
Artificial Intelligence

Boolean Decision Rules via Column Generation

This paper considers the learning of Boolean rules in either disjunctive normal form (DNF, OR-of-ANDs, equivalent to decision rule sets) or conjuncti…
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