output
19922026
Showing 2019 · cs.LGShow all

60 papers · 2 filters

cs.LG2019★ 1 cited

Location Trace Privacy Under Conditional Priors

Casey Meehan, Kamalika Chaudhuri

Providing meaningful privacy to users of location based services is particularly challenging when multiple locations are revealed in a short period of time. This is primarily due t…

cs.LG2019★ 5 cited

RoNGBa: A Robustly Optimized Natural Gradient Boosting Training Approach with Leaf Number Clipping

Liliang Ren, Gen Sun, Jiaman Wu

Natural gradient has been recently introduced to the field of boosting to enable the generic probabilistic predication capability. Natural gradient boosting shows promising perform…

cs.LG2019★ 1 cited

ExperienceThinking: Constrained Hyperparameter Optimization based on Knowledge and Pruning

Chunnan Wang, Hongzhi Wang, Chang Zhou +1

Machine learning algorithms are very sensitive to the hyperparameters, and their evaluations are generally expensive. Users desperately need intelligent methods to quickly optimize…

cs.LG2019★ 18 cited

State Alignment-based Imitation Learning

Fangchen Liu, Zhan Ling, Tongzhou Mu +1

Consider an imitation learning problem that the imitator and the expert have different dynamics models. Most of the current imitation learning methods fail because they focus on im…

cs.LG2019★ 1 cited

ASCAI: Adaptive Sampling for acquiring Compact AI

Mojan Javaheripi, Mohammad Samragh, Tara Javidi +1

This paper introduces ASCAI, a novel adaptive sampling methodology that can learn how to effectively compress Deep Neural Networks (DNNs) for accelerated inference on resource-cons…

cs.LG2019★ 3 cited

Data Generation for Neural Programming by Example

Judith Clymo, Haik Manukian, Nathanaël Fijalkow +2

Programming by example is the problem of synthesizing a program from a small set of input / output pairs. Recent works applying machine learning methods to this task show promise,…

cs.LG2019★ 3 cited

Optimal Robust Learning of Discrete Distributions from Batches

Ayush Jain, Alon Orlitsky

Many applications, including natural language processing, sensor networks, collaborative filtering, and federated learning, call for estimating discrete distributions from data col…

cs.LG2019★ 4 cited

Information-Theoretic Local Minima Characterization and Regularization

Zhiwei Jia, Hao Su

Recent advances in deep learning theory have evoked the study of generalizability across different local minima of deep neural networks (DNNs). While current work focused on either…

cs.LG2019★ 4 cited

Unified Sample-Optimal Property Estimation in Near-Linear Time

Yi Hao, Alon Orlitsky

We consider the fundamental learning problem of estimating properties of distributions over large domains. Using a novel piecewise-polynomial approximation technique, we derive the…

cs.LG2019★ 1 cited

Mapper Based Classifier

Jacek Cyranka, Alexander Georges, David Meyer

Topological data analysis aims to extract topological quantities from data, which tend to focus on the broader global structure of the data rather than local information. The Mappe…

cs.LG2019★ 2 cited

Neural Program Synthesis By Self-Learning

Yifan Xu, Lu Dai, Udaikaran Singh +2

Neural inductive program synthesis is a task generating instructions that can produce desired outputs from given inputs. In this paper, we focus on the generation of a chunk of ass…

cs.LG2019★ 13 cited

Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling

Che Wang, Yanqiu Wu, Quan Vuong +1

We aim to develop off-policy DRL algorithms that not only exceed state-of-the-art performance but are also simple and minimalistic. For standard continuous control benchmarks, Soft…

cs.LG2019★ 3 cited

A Deep Factorization of Style and Structure in Fonts

Nikita Srivatsan, Jonathan T. Barron, Dan Klein +1

We propose a deep factorization model for typographic analysis that disentangles content from style. Specifically, a variational inference procedure factors each training glyph int…

cs.LG2019

A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text

Bohan Li, Junxian He, Graham Neubig +2

When trained effectively, the Variational Autoencoder (VAE) is both a powerful language model and an effective representation learning framework. In practice, however, VAEs are tra…

cs.LG2019★ 27 cited

Improved Schemes for Episodic Memory-based Lifelong Learning

Yunhui Guo, Mingrui Liu, Tianbao Yang +1

Current deep neural networks can achieve remarkable performance on a single task. However, when the deep neural network is continually trained on a sequence of tasks, it seems to g…

cs.LG2019★ 10 cited

Multi-task Batch Reinforcement Learning with Metric Learning

Jiachen Li, Quan Vuong, Shuang Liu +5

We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks…

cs.LG2019★ 3 cited

Nearly Tight Bounds for Robust Proper Learning of Halfspaces with a Margin

Ilias Diakonikolas, Daniel M. Kane, Pasin Manurangsi

We study the problem of {\em properly} learning large margin halfspaces in the agnostic PAC model. In more detail, we study the complexity of properly learning -dimensional half…

cs.LG2019★ 6 cited

Hotel Recommendation System

Aditi A. Mavalankar, Ajitesh Gupta, Chetan Gandotra +1

One of the first things to do while planning a trip is to book a good place to stay. Booking a hotel online can be an overwhelming task with thousands of hotels to choose from, for…

cs.LG2019★ 30 cited

Mapping State Space using Landmarks for Universal Goal Reaching

Zhiao Huang, Fangchen Liu, Hao Su

An agent that has well understood the environment should be able to apply its skills for any given goals, leading to the fundamental problem of learning the Universal Value Functio…

cs.LG2019★ 2 cited

Predicting Eating Events in Free Living Individuals -- A Technical Report

Jiayi Wang, Jiue-An Yang, Supun Nakandala +2

This technical report records the experiments of applying multiple machine learning algorithms for predicting eating and food purchasing behaviors of free-living individuals. Data…

cs.LG2019★ 17 cited

Visualizing the PHATE of Neural Networks

Scott Gigante, Adam S. Charles, Smita Krishnaswamy +1

Understanding why and how certain neural networks outperform others is key to guiding future development of network architectures and optimization methods. To this end, we introduc…

cs.LG2019★ 62 cited

AdaCliP: Adaptive Clipping for Private SGD

Venkatadheeraj Pichapati, Ananda Theertha Suresh, Felix X. Yu +2

Privacy preserving machine learning algorithms are crucial for learning models over user data to protect sensitive information. Motivated by this, differentially private stochastic…

cs.LG2019★ 5 cited

Unexpected Effects of Online no-Substitution k-means Clustering

Michal Moshkovitz

Offline k-means clustering was studied extensively, and algorithms with a constant approximation are available. However, online clustering is still uncharted. New factors come into…

cs.LG2019★ 111 cited

On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift

Alekh Agarwal, Sham M. Kakade, Jason D. Lee +1

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about ev…