BEGIN:VCALENDAR VERSION:2.0 PRODID:-//IFDS - ECPv6.0.1.1//NONSGML v1.0//EN CALSCALE:GREGORIAN METHOD:PUBLISH X-ORIGINAL-URL:https://ifds.info X-WR-CALDESC:Events for IFDS REFRESH-INTERVAL;VALUE=DURATION:PT1H X-Robots-Tag:noindex X-PUBLISHED-TTL:PT1H BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT TZOFFSETFROM:-0800 TZOFFSETTO:-0700 TZNAME:PDT DTSTART:20210314T100000 END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:-0700 TZOFFSETTO:-0800 TZNAME:PST DTSTART:20211107T090000 END:STANDARD BEGIN:DAYLIGHT TZOFFSETFROM:-0800 TZOFFSETTO:-0700 TZNAME:PDT DTSTART:20220313T100000 END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:-0700 TZOFFSETTO:-0800 TZNAME:PST DTSTART:20221106T090000 END:STANDARD TZID:America/Chicago BEGIN:DAYLIGHT TZOFFSETFROM:-0600 TZOFFSETTO:-0500 TZNAME:CDT DTSTART:20220313T080000 END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:-0500 TZOFFSETTO:-0600 TZNAME:CST DTSTART:20221106T070000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20221202T133000 DTEND;TZID=America/Los_Angeles:20221202T133000 DTSTAMP:20260414T235129 CREATED:20221018T165647Z LAST-MODIFIED:20221018T170145Z UID:2321-1669987800-1669987800@ifds.info SUMMARY:IFDS All-Hands DESCRIPTION: URL:https://ifds.info/event/ifds-all-hands-3/ LOCATION:University of Washington\, Seattle\, 185 E Stevens Way NE\, Seattle\, WA\, 98195-2350\, United States CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20221104T133000 DTEND;TZID=America/Los_Angeles:20221104T133000 DTSTAMP:20260414T235129 CREATED:20221018T165642Z LAST-MODIFIED:20221018T165811Z UID:2317-1667568600-1667568600@ifds.info SUMMARY:IFDS All-Hands DESCRIPTION: URL:https://ifds.info/event/ifds-all-hands-2/ LOCATION:University of Washington\, Seattle\, 185 E Stevens Way NE\, Seattle\, WA\, 98195-2350\, United States CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20220304T123000 DTEND;TZID=America/Los_Angeles:20220304T133000 DTSTAMP:20260414T235129 CREATED:20220325T194131Z LAST-MODIFIED:20220325T200316Z UID:1904-1646397000-1646400600@ifds.info SUMMARY:IFDS All-Hands: Zaid Harchaoui DESCRIPTION: URL:https://ifds.info/event/ifds-all-hands-zaid-harchaoui-2/ LOCATION:WA CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20220204T123000 DTEND;TZID=America/Los_Angeles:20220204T133000 DTSTAMP:20260414T235129 CREATED:20220325T195559Z LAST-MODIFIED:20220325T195650Z UID:1915-1643977800-1643981400@ifds.info SUMMARY:IFDS Monthly All-Hands: Rebecca Willett DESCRIPTION:Speaker: Prof. Rebecca Willett\, Statistics and CS\, University of Chicago   \nTitle: The Role of Linear Layers in Nonlinear Interpolating Networks   \nAbstract: In this discussion\, we will explore the implicit bias of overparameterized neural networks of depth greater than two layers. Our framework considers a family of networks of varying depth that all have the same capacity but different implicitly defined representation costs. The representation cost of a function induced by a neural network architecture is the minimum sum of squared weights needed for the network to represent the function; it reflects the function space bias associated with the architecture. Our results show that adding linear layers to a ReLU network yields a representation cost that reflects a complex interplay between the alignment and sparsity of ReLU units. Specifically\, using a neural network to fit training data with minimum representation cost yields an interpolating function that is constant in directions perpendicular to a low-dimensional subspace on which a parsimonious interpolant exists. This is joint work with Greg Ongie. URL:https://ifds.info/event/ifds-monthly-all-hands-rebecca-willett/ LOCATION:WA CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Chicago:20220107T153000 DTEND;TZID=America/Chicago:20220107T163000 DTSTAMP:20260414T235129 CREATED:20220106T152210Z LAST-MODIFIED:20220130T024429Z UID:1739-1641569400-1641573000@ifds.info SUMMARY:IFDS All-Hands: Sébastien Roche DESCRIPTION:Title: Phylogenomics: “Inverting” Random Trees\n\nSpeaker: Sebastien Roch\, UW-Madison\, Department of Mathematics\n\nAbstract: The estimation of species phylogenies from genome-scale data is an important step in modern evolutionary studies. This estimation is complicated by the fact that genes evolve under biological processes that produce discordant trees. Such processes include horizontal gene transfer\, incomplete lineage sorting\, and gene duplication and loss\, all of which can be modeled using certain random tree distributions. I will discuss recent results on the identifiability\, or “invertibility”\, of these probabilistic models. I will also consider the large-sample properties of species tree estimation methods in this context. Based partly on joint works with Max Bacharach\, Brandon Legried\, Erin Molloy\, Elchanan Mossel\, Allan Sly\, Tandy Warnow\, Shuqi Yu.  \n\nBio: Sebastien Roch is a Professor in the Department of Mathematics at University of Wisconsin-Madison\, where he is also affiliated with the Department of Statistics and the Theory of Computing. He earned his Ph.D. in Statistics from the University of California\, Berkeley under the guidance of Elchanan Mossel. From 2007-2009\, he was a Postdoctoral Researcher at Microsoft Research. From 2009-2012\, he was a tenure-track Assistant Professor in the Department of Mathematics at the University of California-Los Angeles. He is the recipient of an NSF CAREER Award and of an Alfred P. Sloan Fellowship. He was a Kavli Fellow of the National Academy of Sciences in 2014 and 2017\, and was a 2018 Simons Fellow. He also received the Best Paper Award at RECOMB 2018. His research interests lie at the interface of applied probability\, statistics\, and theoretical computer science with an emphasis on biological applications. URL:https://ifds.info/event/ifds-all-hands-sebastien-roche/ LOCATION:Zoom CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20220107T123000 DTEND;TZID=America/Los_Angeles:20220107T133000 DTSTAMP:20260414T235129 CREATED:20220325T200214Z LAST-MODIFIED:20220325T200231Z UID:1927-1641558600-1641562200@ifds.info SUMMARY:IFDS Monthly All-Hands: Sebastien Roch DESCRIPTION:Speaker: Prof. Sebastien Roch\, UW-Madison\, Department of Mathematics   \nTitle: Phylogenomics: “Inverting” Random Trees   \nAbstract: The estimation of species phylogenies from genome-scale data is an important step in modern evolutionary studies. This estimation is complicated by the fact that genes evolve under biological processes that produce discordant trees. Such processes include horizontal gene transfer\, incomplete lineage sorting\, and gene duplication and loss\, all of which can be modeled using certain random tree distributions. I will discuss recent results on the identifiability\, or “invertibility”\, of these probabilistic models. I will also consider the large-sample properties of species tree estimation methods in this context. Based partly on joint works with Max Bacharach\, Brandon Legried\, Erin Molloy\, Elchanan Mossel\, Allan Sly\, Tandy Warnow\, Shuqi Yu.     URL:https://ifds.info/event/ifds-monthly-all-hands-sebastien-roch/ LOCATION:WA CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20211203T133000 DTEND;TZID=America/Los_Angeles:20211203T143000 DTSTAMP:20260414T235129 CREATED:20211201T172618Z LAST-MODIFIED:20211201T172618Z UID:1720-1638538200-1638541800@ifds.info SUMMARY:IFDS All-Hands: Marcella Gomez\, UCSC Applied Math DESCRIPTION:Title: Open problems in mathematical modeling and control of wound healing \nAbstract:  Wound healing consists of a series of overlapping biological process with sophisticated coordination to promote wound closure.  Our research work currently focuses on the task of accelerating wound healing by targeting and artificially manipulating key biological processes.  In particular\, we aim to develop models and control architectures for real-time feedback control for accelerated wound closure. In this talk\, I discuss the progress and challenges of working with a complex biological process with limited data\, as well as\, developing feedback control algorithms for systems interfaced with a bioelectronic device and limited observable states. \nBio: Marcella M. Gomez is an associate professor at UC Santa Cruz in the department of Applied Mathematics. She received her PhD from Caltech in 2015 and a B.S. from UC Berkeley in 2009; both degrees in Mechanical Engineering. Her research interests are in synthetic and systems biology. In particular\, she is interested in developing data-driven methods and foundations for modeling and control of complex biological systems.  \nZoom link via email or contact organizer. URL:https://ifds.info/event/ifds-all-hands-marcella-gomez-ucsc-applied-math/ LOCATION:WA CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20211105T133000 DTEND;TZID=America/Los_Angeles:20211105T143000 DTSTAMP:20260414T235129 CREATED:20211105T170055Z LAST-MODIFIED:20211105T173204Z UID:1714-1636119000-1636122600@ifds.info SUMMARY:IFDS All-Hands: Kevin Jamieson DESCRIPTION:Title: Instance Dependent Sample Complexity Bounds for Interactive Learning \n\n\n\nAbstract: The sample complexity of an interactive learning problem\, such as multi-armed bandits or reinforcement learning\, is the number of interactions with nature required to output an answer (e.g.\, a recommended arm or policy) that is approximately close to optimal with high probability. While minimax guarantees can be useful rules of thumb to gauge the difficulty of a problem class\, algorithms optimized for this worst-case metric often fail to adapt to “easy” instances where fewer samples suffice. In this talk\, I will highlight some of my group’s work on algorithms that obtain optimal\, finite time\, instance dependent sample complexities that scale with the true difficulty of the particular instance\, versus just the worst-case. In particular\, I will describe a unifying experimental design based approach used to obtain such algorithms for best-arm identification for linear bandits\, contextual bandits with arbitrary policy classes\, and smooth losses for linear dynamical systems. \n\n\n\nKevin’s website: https://homes.cs.washington.edu/~jamieson/about.html \n\n\nZoom link:  contact organizer \n\n\n(The talk will not be recorded\, we hope you can join us live!) URL:https://ifds.info/event/ifds-all-hands-kevin-jamieson/ LOCATION:WA CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20211008T133000 DTEND;TZID=America/Los_Angeles:20211008T143000 DTSTAMP:20260414T235129 CREATED:20211008T211805Z LAST-MODIFIED:20211008T211902Z UID:1691-1633699800-1633703400@ifds.info SUMMARY:IFDS All-Hands: Qin Li DESCRIPTION:Title:\nMean field theory in Inverse Problems from Bayesian inference to overparameterization of networks \n\nAbstract:\nBayesian sampling and neural networks are seemingly two different machine learning areas\, but they both deal with many particle systems. In sampling\, one evolves a large number of samples (particles) to match a target distribution function\, and in optimizing over-parameterized neural networks\, one can view neurons particles that feed each other information in the DNN flow. These perspectives allow us to employ mean-field theory\, a powerful tool that translates dynamics of many particle system into a partial differential equation (PDE)\, so rich PDE analysis techniques can be used to understand both the convergence of sampling methods and the zero-loss property of over-parameterization of ResNets. We showcase the use of mean-field theory in these two machine learning areas\, and we also invite the audience to brainstorm other possible applications. URL:https://ifds.info/event/ifds-all-hands-qin-li/ LOCATION:WA CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20210507T133000 DTEND;TZID=America/Los_Angeles:20210507T143000 DTSTAMP:20260414T235129 CREATED:20210504T203604Z LAST-MODIFIED:20210504T203845Z UID:1230-1620394200-1620397800@ifds.info SUMMARY:IFDS All-Hands: Rina Foygel Barber DESCRIPTION:Convergence for nonconvex ADMM\, with applications to CT imaging\nThe alternating direction method of multipliers (ADMM) algorithm is a powerful and flexible tool for complex optimization problems of the form min{f(x)+g(y):Ax+By=c}. ADMM exhibits robust empirical performance across a range of challenging settings including nonsmoothness and nonconvexity of the objective functions f and g\, and provides a simple and natural approach to the inverse problem of image reconstruction for computed tomography (CT) imaging. From the theoretical point of view\, existing results for convergence in the nonconvex setting generally assume smoothness in at least one of the component functions in the objective. In this work\, our new theoretical results provide convergence guarantees under a restricted strong convexity assumption without requiring smoothness or differentiability\, while still allowing differentiable terms to be treated approximately if needed. We validate these theoretical results empirically\, with a simulated example where both f and g are nondifferentiable (and thus outside the scope of existing theory)\, as well as a simulated CT image reconstruction problem. \n\n\nBio: Rina Foygel Barber is a Louis Block Professor in the Department of Statistics at the University of Chicago. She was a NSF postdoctoral fellow during 2012-13 in the Department of Statistics at Stanford University\, supervised by Emmanuel Candès. She received her PhD in Statistics at the University of Chicago in 2012\, advised by Mathias Drton and Nati Srebro\, and a MS in Mathematics at the University of Chicago in 2009. Prior to graduate school\, she was a mathematics teacher at the Park School of Baltimore from 2005 to 2007. URL:https://ifds.info/event/ifds-all-hands-rina-foygel-barber/ LOCATION:WA CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20210402T133000 DTEND;TZID=America/Los_Angeles:20210402T143000 DTSTAMP:20260414T235129 CREATED:20210115T201436Z LAST-MODIFIED:20210331T134630Z UID:880-1617370200-1617373800@ifds.info SUMMARY:IFDS All-Hands: Chaobing Song & Xuezhou Zhang DESCRIPTION:Speaker 1: Dr. Chaobing Song\, IFDS Postdoctoral Scholar at U Wisconsin (advised by Prof.s Jelena Diakonikolas and Steve Wright)\n\nTitle: Closing Convergence Gaps for Both Smooth and Nonsmooth Convex Finite-Sums\n \nAbstract: In the Foundation of Data Science\, optimization problems with a finite-sum structure widely exist\, such as the classical empirical risk minimization problem and deep neural network. In the past decade\, one main concern in the study of first-order methods is to study how the finite-sum structure influences optimization efficiency and scalability. In this talk\, based on my work (https://arxiv.org/abs/2006.10281\, https://arxiv.org/abs/2102.13643)\, I will talk about a consistent approach based on dual averaging and a particularly designed initialization strategy to close convergence gaps for smooth convex finite-sums and nonsmooth convex finite-sums. For the first time\, the proposed VRADA algorithm (https://arxiv.org/abs/2006.10281) matches the lower bounds of all the three regimes for smooth convex finite-sums; for the first time\, the proposed VRPDA^2 algorithm  (https://arxiv.org/abs/2102.13643) shows an O(n) improvement theoretically over existing deterministic methods and stochastic primal-dual coordinate methods\, where n is the number of data samples. Both algorithms also have good empirical performance.\n\n \nSpeaker 2: Xuezhou Zhang\, IFDS RA (advised by Prof. Jerry Zhu)\n \n\nTitle: Statistical Robustness in Reinforcement Learning\n \nAbstract: Traditional robust statistics studies the problem of statistical estimation under data contamination. In this talk\, we extend this investigation to decision-making problems. In the first half of the talk\, I will illustrate the concept and unique challenge of robust Decision making using a multi-armed bandit as an example. In the second half of the talk\, I will present some of the lower and upper-bound results we have already established\, and discuss several open directions. This talk is partially based on our recent paper [https://arxiv.org/pdf/2102.05800.pdf].\n\n \n\n—-\nSpeaker Bios:\n \nDr. Chaobing Song: I am a postdoc researcher at University of Wisconsin-Madison with Prof. Jelena Diakonikolas and Prof. Stephen J Wright. My research interests include optimization and machine learning. I obtained my Ph.D. degree at Tsinghua University in 2020 supervised by Prof. Yi Ma from University of California\, Berkeley (who is an affiliate professor at Tsinghua-Berkeley Shenzhen Institute\, Tsinghua University). I spent two wonderful years at Berkeley and finished my Ph.D. thesis there. The main focus of my current research is to apply a general\, powerful and concise framework [arXiv] to optimization problems in machine learning. The development based on this framework substantially improves complexity results in many well-known settings\, such as the setting of nonsmooth convex finite-sums in this talk.  \n \nXuezhou Zhang: Xuezhou is a Ph.D. candidate in the computer sciences department at the University of Wisconsin-Madison\, advised by Professor Jerry Zhu. Before coming to Madison\, he obtained a Bachelor of Applied Mathematics degree from UCLA. His research interests lie in machine learning and reinforcement learning\, and his recent research focuses on designing reinforcement learning algorithms that learn more adaptively and robustly in non-stochastic environments.\n\nThese talks are remote via zoom. Please contact the organizer if you need the link. \nAll-Hands titles and abstracts are tentative\, as of the posting date. URL:https://ifds.info/event/ifds-all-hands-040221/ LOCATION:WA CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20210305T133000 DTEND;TZID=America/Los_Angeles:20210305T143000 DTSTAMP:20260414T235129 CREATED:20210115T200409Z LAST-MODIFIED:20210305T213122Z UID:867-1614951000-1614954600@ifds.info SUMMARY:IFDS All-Hands: Yang Liu DESCRIPTION:Prof. Yang Liu\, Computer Science Dept\, UC Santa Cruz \nTitle: Consequential Machine Learning \nAbstract: Recent findings cautioned the potential unfairness issues that can arise when deploying a machine learning model. Correspondingly\, treatments have been proposed to add fairness guarantees when training such statistical models. An often overlooked question is “what after?” One can discover ways to improve the model after deployment\, and after receiving feedback from human subjects that saw these algorithmic treatments. But the unfortunate fact is once a model is deployed\, it will start to impact a later decision and the society for a long period of time. In this talk\, I am going to introduce some of the recent works that initialize our attempt to understand the consequences of the deployment of a machine learning algorithm. We will first show that an appeared-to-be fair algorithm might not necessarily help reduce disparities among societal groups that we aim to protect. The long-term impacts of a sequence of deployments of machine learning models will depend on the induced dynamics of the underlying populations’ qualification. Then I discuss how to use the design and deployment of machine learning to induce proper dynamics by offering human agents actionable recourse to improve their qualifications. \nAll Hands titles and abstracts are tentative\, as of the posting date. URL:https://ifds.info/event/ifds-monthly-all-hands-2/ LOCATION:WA CATEGORIES:Monthly All-Hands END:VEVENT BEGIN:VEVENT DTSTART;TZID=America/Los_Angeles:20210205T133000 DTEND;TZID=America/Los_Angeles:20210205T143000 DTSTAMP:20260414T235129 CREATED:20210115T155014Z LAST-MODIFIED:20210205T134755Z UID:845-1612531800-1612535400@ifds.info SUMMARY:IFDS All-Hands: Zaid Harchaoui DESCRIPTION:Zaid Harchaoui\, Associate Professor\, Statistics \nTitle: On statistical estimation\, signal denoising\, and convex optimization \nAbstract: We revisit the classical statistical problem of adaptive discrete-time signal denoising. Conventional nonparametric statistics and signal processing approaches rely on strong structural assumptions on the signal set. The approach we present\, inspired by the seminal works from Ibragimov-Khasminskii and later Donoho\, takes a different view and focuses instead on statistical estimators amenable to convex optimization. We show that such estimators possess better statistical properties than conventional ones. In particular\, under an assumption of approximate shift-invariance\, the proposed estimators enjoy l2-loss oracle inequalities. We show how to implement them using optimal first-order methods and highlight interesting statistical-computational trade-offs. Joint work with D. Ostrovskii\, A. Juditsky\, A. Nemirovski.  \n  URL:https://ifds.info/event/ifds-all-hands-zaid-harchaoui/ LOCATION:WA CATEGORIES:Monthly All-Hands END:VEVENT END:VCALENDAR