scispace - formally typeset
Search or ask a question
Author

Robert Tibshirani

Bio: Robert Tibshirani is an academic researcher from Stanford University. The author has contributed to research in topics: Lasso (statistics) & Elastic net regularization. The author has an hindex of 147, co-authored 593 publications receiving 326580 citations. Previous affiliations of Robert Tibshirani include University of Toronto & University of California.


Papers
More filters
Posted Content
TL;DR: This work presents a method that exploits any existing relationship between between illness severity and treatment effect, and searches for the "sweet spot", the contiguous range of illness severity where the estimated treatment benefit is maximized.
Abstract: Identifying heterogeneous treatment effects (HTEs) in randomized controlled trials is an important step toward understanding and acting on trial results. However, HTEs are often small and difficult to identify, and HTE modeling methods which are very general can suffer from low power. We present a method that exploits any existing relationship between illness severity and treatment effect, and identifies the "sweet spot", the contiguous range of illness severity where the estimated treatment benefit is maximized. We further compute a bias-corrected estimate of the conditional average treatment effect (CATE) in the sweet spot, and a $p$-value. Because we identify a single sweet spot and $p$-value, we believe our method to be straightforward to interpret and actionable: results from our method can inform future clinical trials and help clinicians make personalized treatment recommendations.

1 citations

Journal ArticleDOI
TL;DR: A new method for supervised learning that fits a hub-based graphical model to the predictors, to estimate the amount of “connection” that each predictor has with other predictors that yields a set of predictor weights that are used in a regularized regression such as the lasso or elastic net.
Abstract: We propose a new method for supervised learning. The hubNet procedure fits a hub-based graphical model to the predictors, to estimate the amount of “connection” that each predictor has with other predictors. This yields a set of predictor weights that are then used in a regularized regression such as the lasso or elastic net. The resulting procedure is easy to implement, can often yield higher or competitive prediction accuracy with fewer features than the lasso, and can give insight into the underlying structure of the predictors. HubNet can be generalized seamlessly to supervised problems such as regularized logistic regression (and other GLMs), Cox’s proportional hazards model, and nonlinear procedures such as random forests and boosting. We prove recovery results under a specialized model and illustrate the method on real and simulated data. HubNet; Adaptive Lasso; Graphical Model; Unsupervised Weights

1 citations

26 Jan 2022
TL;DR: Out-of-bag error is commonly used as an estimate of generalisation error in ensemble-based learning models such as random forests and it is shown that these new confidence intervals have improved coverage properties over the näıve confidence interval, in real and simulated examples.
Abstract: Out-of-bag error is commonly used as an estimate of generalisation error in ensemble-based learning models such as random forests. We present confidence intervals for this quantity using the delta-method-after-bootstrap and the jackknife-after-bootstrap techniques. These methods do not require growing any additional trees. We show that these new confidence intervals have improved coverage properties over the naive confidence interval, in real and simulated examples.

1 citations

Posted ContentDOI
28 Apr 2022-bioRxiv
TL;DR: An interpretive framework is developed that screens for multiple illnesses simultaneously and independently recapitulate known biology of the responses to infection by SARS-CoV-2 or HIV, and reveal common features of autoreactive immune receptor repertoires, indicating that machine learning on immune repertoires can yield new immunological knowledge.
Abstract: Clinical diagnoses rely on a wide variety of laboratory tests and imaging studies, interpreted alongside physical examination findings and the patient’s history and symptoms. Currently, the tools of diagnosis make limited use of the immune system’s internal record of specific disease exposures encoded by the antigen-specific receptors of memory B cells and T cells, and there has been little integration of the combined information from B cell and T cell receptor sequences. Here, we analyze extensive receptor sequence datasets with three different machine learning representations of immune receptor repertoires to develop an interpretive framework, MAchine Learning for Immunological Diagnosis (Mal-ID), that screens for multiple illnesses simultaneously. This approach is effective in identifying a variety of disease states, including acute and chronic infections and autoimmune disorders. It is able to do so even when there are other differences present in the immune repertoires, such as between pediatric or adult patient groups. Importantly, many features of the model of immune receptor sequences are human-interpretable. They independently recapitulate known biology of the responses to infection by SARS-CoV-2 and HIV, provide evidence of receptor antigen specificity, and reveal common features of autoreactive immune receptor repertoires, indicating that machine learning on immune repertoires can yield new immunological knowledge. This framework could be useful in identifying immune responses to new infectious diseases as they emerge.

1 citations

Posted ContentDOI
21 Feb 2022-bioRxiv
TL;DR: This work challenges chemotaxing HL60 neutrophil-like cells with symmetric bifurcating microfluidic channels and suggests a “selective listening” model in which both actively protruding cell fronts and actively retracting cell rears have strong commitment to their current migratory program.
Abstract: As neutrophils navigate complex environments to reach sites of infection, they may encounter obstacles that force them to split their front into multiple leading edges, raising the question of how the cell selects which front to maintain and which front(s) to abandon. Here we challenge chemotaxing HL60 neutrophil-like cells with symmetric bifurcating microfluidic channels, enabling us to probe the cell-intrinsic properties of their decision-making process. Using supervised statistical learning, we demonstrate that cells commit to one leading edge late in the decision- making process, rather than amplifying early pre-existing asymmetries. Furthermore, we use optogenetic tools to show that receptor inputs only bias the decision similarly late, once mechanical stretching begins to weaken each front. Finally, optogenetic attempts to reverse cell decisions reveal that, once an edge begins retracting, it commits to this fate, with the kinase ROCK limiting its sensitivity to inputs until the retraction is complete. Collectively our results suggest a “selective listening” model in which both actively protruding cell fronts and actively retracting cell rears have strong commitment to their current migratory program.

1 citations


Cited by
More filters
Journal Article
TL;DR: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems, focusing on bringing machine learning to non-specialists using a general-purpose high-level language.
Abstract: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic and commercial settings. Source code, binaries, and documentation can be downloaded from http://scikit-learn.sourceforge.net.

47,974 citations

Journal ArticleDOI
TL;DR: This work presents DESeq2, a method for differential analysis of count data, using shrinkage estimation for dispersions and fold changes to improve stability and interpretability of estimates, which enables a more quantitative analysis focused on the strength rather than the mere presence of differential expression.
Abstract: In comparative high-throughput sequencing assays, a fundamental task is the analysis of count data, such as read counts per gene in RNA-seq, for evidence of systematic changes across experimental conditions. Small replicate numbers, discreteness, large dynamic range and the presence of outliers require a suitable statistical approach. We present DESeq2, a method for differential analysis of count data, using shrinkage estimation for dispersions and fold changes to improve stability and interpretability of estimates. This enables a more quantitative analysis focused on the strength rather than the mere presence of differential expression. The DESeq2 package is available at http://www.bioconductor.org/packages/release/bioc/html/DESeq2.html .

47,038 citations

Journal ArticleDOI
TL;DR: A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.
Abstract: SUMMARY We propose a new method for estimation in linear models. The 'lasso' minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant. Because of the nature of this constraint it tends to produce some coefficients that are exactly 0 and hence gives interpretable models. Our simulation studies suggest that the lasso enjoys some of the favourable properties of both subset selection and ridge regression. It produces interpretable models like subset selection and exhibits the stability of ridge regression. There is also an interesting relationship with recent work in adaptive function estimation by Donoho and Johnstone. The lasso idea is quite general and can be applied in a variety of statistical models: extensions to generalized regression models and tree-based models are briefly described.

40,785 citations

Proceedings ArticleDOI
07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

40,257 citations

Book
18 Nov 2016
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

38,208 citations