[Theory] REMINDER: 2/16 Talks at TTIC: Jonathan Warrell, Yale University

[Mary Marre]

*When:*      Tuesday, February 16th at* 11:10 am CT*



*Where:*     Zoom Virtual Talk (*register in advance here
<https://uchicagogroup.zoom.us/webinar/register/WN_6LU_3OPgR4yFdkQ2omffXg>*)



*Who: *       Jonathan Warrell, Yale University


*Title:* Interpretability and Higher-order Generalization in Deep Learning:
Integrated models of Genomics, Evolution and the Brain

*Abstract: *A gap has emerged in many domains between the performance of
the most predictive models, which are typically deep neural networks, and
models whose parameters are readily interpretable.  This gap raises
questions concerning which assumptions embedded in deep learning models /
training algorithms allow them to generalize so well, what such assumptions
correspond to semantically in particular domains, and how we might use such
implicit semantics to gain new knowledge about a domain.  I will discuss
these issues from a PAC-Bayes viewpoint, particularly focusing on how model
architectures, incorporation of prior knowledge, and compressibility /
complexity control can be motivated by these considerations in the context
of genomics and neuroscience.  In the process, I will introduce a
type-theoretic framework based on probabilistic programming for deriving
higher-order generalization bounds.  These learn a hierarchy of model
complexity measures for individual tasks or groups of tasks, which combine
compressibility and domain specific constraints (e.g. from physical models)
in order to provide optimal biases during training.  I will then outline
case studies for how the issues discussed have led me to explore both
hand-designed architectures / algorithms for extracting semantics out of
interpretable models in particular domains, and *de novo* variational-based
approaches using the higher-order generalization bounds I propose.  These
case studies include developing integrated models of genetic risk for
psychiatric disorders and cognition as part of the NIH PsychENCODE
consortium (including genetic, epigenetic, cellular and brain imaging
data), detecting positive and negative selection in cancer, and identifying
latent evolutionary structure in genomics and cultural domains.

*Bio: *Jonathan Warrell is a postdoctoral associate research scientist in
the Computational Biology and Bioinformatics program at Yale University,
working with Mark Gerstein.  He has published extensively in computational
biology, machine learning, computer vision, and theoretical biology and
evolution.  He is currently a member of several large-scale genomics
consortia, including ENCODE, PsychENCODE, and PCAWG (Pan-Cancer Analysis of
Whole Genomes), and his work has been featured in the journals Science and
Cell, as well as conferences such as CVPR, ECCV and ISMB.  Jonathan has
held postdoctoral positions in computer vision and machine learning at
University College London and Oxford / Oxford Brookes Universities, and
computational biology and genomics at University of Cape Town and Yale
University.  He began his academic career in music theory, and holds a BA
in music from Cambridge, an MA and PhD from King's College London in music
theory and analysis, and an MSc in computer science from University College
London.  His current research areas include integrated models of genetic
risk in psychiatric genomics, neuroscience and cancer, interpretable
machine learning, statistical learning theory, and generalized evolutionary
models of gene networks, cancer, and cultural processes.

*Host:* Jinbo Xu <j3xu at ttic.edu>



Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Mon, Feb 15, 2021 at 3:30 PM Mary Marre <mmarre at ttic.edu> wrote:

> *When:*      Tuesday, February 16th at* 11:10 am CT*
>
>
>
> *Where:*     Zoom Virtual Talk (*register in advance here
> <https://uchicagogroup.zoom.us/webinar/register/WN_6LU_3OPgR4yFdkQ2omffXg>*
> )
>
>
>
> *Who: *       Jonathan Warrell, Yale University
>
>
> *Title:* Interpretability and Higher-order Generalization in Deep
> Learning: Integrated models of Genomics, Evolution and the Brain
>
> *Abstract: *A gap has emerged in many domains between the performance of
> the most predictive models, which are typically deep neural networks, and
> models whose parameters are readily interpretable.  This gap raises
> questions concerning which assumptions embedded in deep learning models /
> training algorithms allow them to generalize so well, what such assumptions
> correspond to semantically in particular domains, and how we might use such
> implicit semantics to gain new knowledge about a domain.  I will discuss
> these issues from a PAC-Bayes viewpoint, particularly focusing on how model
> architectures, incorporation of prior knowledge, and compressibility /
> complexity control can be motivated by these considerations in the context
> of genomics and neuroscience.  In the process, I will introduce a
> type-theoretic framework based on probabilistic programming for deriving
> higher-order generalization bounds.  These learn a hierarchy of model
> complexity measures for individual tasks or groups of tasks, which combine
> compressibility and domain specific constraints (e.g. from physical models)
> in order to provide optimal biases during training.  I will then outline
> case studies for how the issues discussed have led me to explore both
> hand-designed architectures / algorithms for extracting semantics out of
> interpretable models in particular domains, and *de novo* variational-based
> approaches using the higher-order generalization bounds I propose.  These
> case studies include developing integrated models of genetic risk for
> psychiatric disorders and cognition as part of the NIH PsychENCODE
> consortium (including genetic, epigenetic, cellular and brain imaging
> data), detecting positive and negative selection in cancer, and identifying
> latent evolutionary structure in genomics and cultural domains.
>
> *Bio: *Jonathan Warrell is a postdoctoral associate research scientist in
> the Computational Biology and Bioinformatics program at Yale University,
> working with Mark Gerstein.  He has published extensively in computational
> biology, machine learning, computer vision, and theoretical biology and
> evolution.  He is currently a member of several large-scale genomics
> consortia, including ENCODE, PsychENCODE, and PCAWG (Pan-Cancer Analysis of
> Whole Genomes), and his work has been featured in the journals Science and
> Cell, as well as conferences such as CVPR, ECCV and ISMB.  Jonathan has
> held postdoctoral positions in computer vision and machine learning at
> University College London and Oxford / Oxford Brookes Universities, and
> computational biology and genomics at University of Cape Town and Yale
> University.  He began his academic career in music theory, and holds a BA
> in music from Cambridge, an MA and PhD from King's College London in music
> theory and analysis, and an MSc in computer science from University College
> London.  His current research areas include integrated models of genetic
> risk in psychiatric genomics, neuroscience and cancer, interpretable
> machine learning, statistical learning theory, and generalized evolutionary
> models of gene networks, cancer, and cultural processes.
>
> *Host:* Jinbo Xu <j3xu at ttic.edu>
>
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 517*
> *Chicago, IL  60637*
> *p:(773) 834-1757*
> *f: (773) 357-6970*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Wed, Feb 10, 2021 at 11:52 AM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:*      Tuesday, February 16th at* 11:10 am CT*
>>
>>
>>
>> *Where:*     Zoom Virtual Talk (*register in advance here
>> <https://uchicagogroup.zoom.us/webinar/register/WN_6LU_3OPgR4yFdkQ2omffXg>*
>> )
>>
>>
>>
>> *Who: *       Jonathan Warrell, Yale University
>>
>>
>> *Title:* Interpretability and Higher-order Generalization in Deep
>> Learning: Integrated models of Genomics, Evolution and the Brain
>>
>> *Abstract:* A gap has emerged in many domains between the performance of
>> the most predictive models, which are typically deep neural networks, and
>> models whose parameters are readily interpretable.  This gap raises
>> questions concerning which assumptions embedded in deep learning models /
>> training algorithms allow them to generalize so well, what such assumptions
>> correspond to semantically in particular domains, and how we might use such
>> implicit semantics to gain new knowledge about a domain.  I will discuss
>> these issues from a PAC-Bayes viewpoint, particularly focusing on how model
>> architectures, incorporation of prior knowledge, and compressibility /
>> complexity control can be motivated by these considerations in the context
>> of genomics and neuroscience.  In the process, I will introduce a
>> type-theoretic framework based on probabilistic programming for deriving
>> higher-order generalization bounds.  These learn a hierarchy of model
>> complexity measures for individual tasks or groups of tasks, which combine
>> compressibility and domain specific constraints (e.g. from physical models)
>> in order to provide optimal biases during training.  I will then outline
>> case studies for how the issues discussed have led me to explore both
>> hand-designed architectures / algorithms for extracting semantics out of
>> interpretable models in particular domains, and *de novo* approaches
>> using the higher-order generalization bounds I propose.  These case studies
>> include developing integrated models of genetic risk for psychiatric
>> disorders and cognition as part of the NIH PsychENCODE consortium
>> (including genetic, epigenetic, cellular and brain imaging data), detecting
>> positive and negative selection in cancer, and identifying latent
>> evolutionary structure in genomics and cultural domains.
>>
>> *Bio: *Jonathan Warrell is a postdoctoral associate research scientist
>> in the Computational Biology and Bioinformatics program at Yale University,
>> working with Mark Gerstein.  He has published extensively in computational
>> biology, machine learning, computer vision, and theoretical biology and
>> evolution.  He is currently a member of several large-scale genomics
>> consortia, including ENCODE, PsychENCODE, and PCAWG (Pan-Cancer Analysis of
>> Whole Genomes), and his work has been featured in the journals Science and
>> Cell, as well as conferences such as CVPR, ECCV and ISMB.  Jonathan has
>> held postdoctoral positions in computer vision and machine learning at
>> University College London and Oxford / Oxford Brookes Universities, and
>> computational biology and genomics at University of Cape Town and Yale
>> University.  He began his academic career in music theory, and holds a BA
>> in music from Cambridge, an MA and PhD from King's College London in music
>> theory and analysis, and an MSc in computer science from University College
>> London.  His current research areas include integrated models of genetic
>> risk in psychiatric genomics, neuroscience and cancer, interpretable
>> machine learning, statistical learning theory, and generalized evolutionary
>> models of gene networks, cancer, and cultural processes.
>>
>> *Host:* Jinbo Xu <j3xu at ttic.edu>
>>
>>
>> Mary C. Marre
>> Faculty Administrative Support
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue*
>> *Room 517*
>> *Chicago, IL  60637*
>> *p:(773) 834-1757*
>> *f: (773) 357-6970*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20210216/24909249/attachment-0001.html>