output
19922026
Showing 2016 · cs.LGShow all

10 papers · 2 filters

cs.LG2016★ 2 cited

S3Pool: Pooling with Stochastic Spatial Sampling

Shuangfei Zhai, Hui Wu, Abhishek Kumar +4

Feature pooling layers (e.g., max pooling) in convolutional neural networks (CNNs) serve the dual purpose of providing increasingly abstract representations as well as yielding com…

cs.LG2016★ 12 cited

Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics

Xi Wu, Fengan Li, Arun Kumar +3

While significant progress has been made separately on analytics systems for scalable stochastic gradient descent (SGD) and private SGD, none of the major scalable analytics framew…

cs.LG2016★ 9 cited

The Extended Littlestone's Dimension for Learning with Mistakes and Abstentions

Chicheng Zhang, Kamalika Chaudhuri

This paper studies classification with an abstention option in the online setting. In this setting, examples arrive sequentially, the learner is given a hypothesis class $\mathcal…

cs.LG2016★ 23 cited

On the Theory and Practice of Privacy-Preserving Bayesian Data Analysis

James Foulds, Joseph Geumlek, Max Welling +1

Bayesian inference has great promise for the privacy-preserving analysis of sensitive data, as posterior sampling automatically preserves differential privacy, an algorithmic notio…

cs.LG2016

Pufferfish Privacy Mechanisms for Correlated Data

Shuang Song, Yizhen Wang, Kamalika Chaudhuri

Many modern databases include personal and sensitive correlated data, such as private information on users connected together in a social network, and measurements of physical acti…

cs.LG2016★ 56 cited

Learning Privately from Multiparty Data

Jihun Hamm, Paul Cao, Mikhail Belkin

Learning a classifier from private data collected by multiple parties is an important problem that has many potential applications. How can we build an accurate and differentially…

cs.LG2016★ 8 cited

Learning to Abstain from Binary Prediction

Akshay Balsubramani

A binary classifier capable of abstaining from making a label prediction has two goals in tension: minimizing errors, and avoiding abstaining unnecessarily often. In this work, we…

cs.LG2016★ 4 cited

Search Improves Label for Active Learning

Alina Beygelzimer, Daniel Hsu, John Langford +1

We investigate active learning with access to two distinct oracles: Label (which is standard) and Search (which is not). The Search oracle models the situation where a human search…

cs.LG2016★ 6 cited

Interactive Bayesian Hierarchical Clustering

Sharad Vikram, Sanjoy Dasgupta

Clustering is a powerful tool in data analysis, but it is often difficult to find a grouping that aligns with a user's needs. To address this, several methods incorporate constrain…

cs.LG2016★ 17 cited

Infomax strategies for an optimal balance between exploration and exploitation

Gautam Reddy, Antonio Celani, Massimo Vergassola

Proper balance between exploitation and exploration is what makes good decisions, which achieve high rewards like payoff or evolutionary fitness. The Infomax principle postulates t…