Search Results for author: Aditya Parameswaran

Found 10 papers, 0 papers with code

Production Machine Learning Pipelines: Empirical Analysis and Optimization Opportunities

no code implementations30 Mar 2021 Doris Xin, Hui Miao, Aditya Parameswaran, Neoklis Polyzotis

Machine learning (ML) is now commonplace, powering data-driven applications in various organizations.

Whither AutoML? Understanding the Role of Automation in Machine Learning Workflows

no code implementations13 Jan 2021 Doris Xin, Eva Yiwei Wu, Doris Jung-Lin Lee, Niloufar Salehi, Aditya Parameswaran

Efforts to make machine learning more widely accessible have led to a rapid increase in Auto-ML tools that aim to automate the process of training and deploying machine learning.

AutoML

Demystifying a Dark Art: Understanding Real-World Machine Learning Model Development

no code implementations4 May 2020 Angela Lee, Doris Xin, Doris Lee, Aditya Parameswaran

It is well-known that the process of developing machine learning (ML) workflows is a dark-art; even experts struggle to find an optimal workflow leading to a high accuracy model.

Helix: Holistic Optimization for Accelerating Iterative Machine Learning

no code implementations14 Dec 2018 Doris Xin, Stephen Macke, Litian Ma, Jialin Liu, Shuchen Song, Aditya Parameswaran

Machine learning workflow development is a process of trial-and-error: developers iterate on workflows by testing out small modifications until the desired accuracy is achieved.

Helix: Accelerating Human-in-the-loop Machine Learning

no code implementations3 Aug 2018 Doris Xin, Litian Ma, Jialin Liu, Stephen Macke, Shuchen Song, Aditya Parameswaran

Data application developers and data scientists spend an inordinate amount of time iterating on machine learning (ML) workflows -- by modifying the data pre-processing, model training, and post-processing steps -- via trial-and-error to achieve the desired model performance.

Structured Prediction

How Developers Iterate on Machine Learning Workflows -- A Survey of the Applied Machine Learning Literature

no code implementations27 Mar 2018 Doris Xin, Litian Ma, Shuchen Song, Aditya Parameswaran

A quantitative characterization of iteration can serve as a benchmark for machine learning workflow development in practice, and can aid the development of human-in-the-loop machine learning systems.

The Importance of Norm Regularization in Linear Graph Embedding: Theoretical Analysis and Empirical Demonstration

no code implementations ICLR 2019 Yihan Gao, Chao Zhang, Jian Peng, Aditya Parameswaran

Both theoretical and empirical evidence are provided to support this argument: (a) we prove that the generalization error of these methods can be bounded by limiting the norm of vectors, regardless of the embedding dimension; (b) we show that the generalization performance of linear graph embedding methods is correlated with the norm of embedding vectors, which is small due to the early stopping of SGD and the vanishing gradients.

Graph Embedding

On the Interpretability of Conditional Probability Estimates in the Agnostic Setting

no code implementations9 Jun 2015 Yihan Gao, Aditya Parameswaran, Jian Peng

We study the interpretability of conditional probability estimates for binary classification under the agnostic setting or scenario.

General Classification

Indexing Cost Sensitive Prediction

no code implementations15 Aug 2014 Leilani Battle, Edward Benson, Aditya Parameswaran, Eugene Wu

We develop algorithms and indexes to support cost-sensitive prediction, i. e., making decisions using machine learning models taking feature evaluation cost into account.

Decision Making

Minimizing Uncertainty in Pipelines

no code implementations NeurIPS 2012 Nilesh Dalvi, Aditya Parameswaran, Vibhor Rastogi

In this paper, we consider the problem of asking the optimal set of queries to minimize the resulting output uncertainty.

Cannot find the paper you are looking for? You can Submit a new open access paper.