BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//IFDS - ECPv6.0.1.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:IFDS
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/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20230312T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20231105T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20240310T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20241103T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20240318T123000
DTEND;TZID=America/Chicago:20240318T133000
DTSTAMP:20260529T230944
CREATED:20240318T214430Z
LAST-MODIFIED:20240318T214430Z
UID:2906-1710765000-1710768600@ifds.info
SUMMARY:IFDS Ideas Forum Double Header
DESCRIPTION:Karan Srivastava\n\n\n\n\nHarit Vishwakarma: “Confidence functions for auto-labeling”
URL:https://ifds.info/event/ifds-ideas-forum-double-header-2/
LOCATION:WID 1145\, 330 N Orchard Street\, Madison\, WI\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20240311T123000
DTEND;TZID=America/Chicago:20240311T133000
DTSTAMP:20260529T230944
CREATED:20240318T214257Z
LAST-MODIFIED:20240318T214257Z
UID:2904-1710160200-1710163800@ifds.info
SUMMARY:Towards Plurality: Learning from Diverse Human Preferences
DESCRIPTION:Speaker: Ramya Vinayak \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nAbstract: \nLarge pre-trained models trained on internet-scale data are often not ready for safe deployment out of the box. They are heavily fine-tuned and aligned using large quantities of human preference data. When we want to align an AI/ML model to human preference or values\,  it is worthwhile to ask whose preference and values we are aligning it to? Recently\, the limitations of current approaches due to their inherent uniformity assumption have been highlighted and the need for plurality – capturing the diversity in human preferences and values – is getting recognized as an important challenge to address. While alignment from human preferences has currently become a very active area of research\, it is worthwhile to note that there is rich literature on learning preferences from human judgements using comparison queries. It plays a crucial role in several applications ranging from cognitive and behavioral psychology\, crowdsourcing democracy\, surveys in social science applications\, and recommendation systems. However\, the models in the literature often focus on learning average preference over the population due to the limitations on the amount of data available per individual and also assume the knowledge of the metric or way humans judge similarity and dissimilarity. \nIn this talk\, I will discuss some recent results that focus on how we can reliably capture diversity in preferences while pooling together data from individuals. In particular\, I will talk about fundamental questions in two directions: (1) Simultaneous metric and preference learning where the goal is to learn an unknown shared metric from preference queries while the preferences are diverse and also unknown. (2) Learning distribution of preferences over a population with a single comparison query per individual. \nBio: \nRamya Korlakai Vinayak is an assistant professor in the Dept. of ECE and affiliated faculty in the Dept. of Computer Science and the Dept. of Statistics at the UW-Madison. Her research interests span the areas of machine learning\, statistical inference\, and crowdsourcing. Her work focuses on addressing theoretical and practical challenges that arise when learning from heterogeneous data from people. Prior to joining UW-Madison\, Ramya was a postdoctoral researcher in the Paul G. Allen School of Computer Science and Engineering at the University of Washington. She received her Ph.D. in Electrical Engineering from Caltech. She obtained her Masters from Caltech and Bachelors from IIT Madras. She is a recipient of the Schlumberger Foundation Faculty of the Future fellowship from 2013-15\, and an invited participant at the Rising Stars in EECS workshop in 2019. She is the recipient of NSF CAREER Award 2023-2028.
URL:https://ifds.info/event/towards-plurality-learning-from-diverse-human-preferences/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20240304T123000
DTEND;TZID=America/Chicago:20240304T133000
DTSTAMP:20260529T230944
CREATED:20240318T214117Z
LAST-MODIFIED:20240318T214117Z
UID:2902-1709555400-1709559000@ifds.info
SUMMARY:IFDS Ideas Forum Double Header
DESCRIPTION:Speaker 1: Puqian Wang \nRobustly Learning Single-Index Models via Alignment Sharpness \nAbstract: We study the problem of learning Single-Index Models under the L_2^2 loss in the agnostic model. We give an efficient learning algorithm\, achieving a constant factor approximation to the optimal loss\, that succeeds under a range of distributions (including log-concave distributions) and a broad class of monotone and Lipschitz link functions. This is the first efficient constant factor approximate agnostic learner\, even for Gaussian data and for any nontrivial class of link functions. Prior work for the case of unknown link function either works in the realizable setting or does not attain constant factor approximation. The main technical ingredient enabling our algorithm and analysis is a novel notion of a local error bound in optimization that we term alignment sharpness and that may be of broader interest. \n  \nSpeaker 2: Lisheng Ren \nSQ Lower Bounds for Non-Gaussian Component Analysis with Weaker Assumptions \nAbstract: The talk focuses on the complexity of Non-Gaussian Component Analysis (NGCA) in the Statistical Query (SQ) model. The NGCA has been a useful problem framework for obtaining SQ hardness for a variety of statistical problems. In particular\, it was previously known that for any univariate distribution $A$ satisfying certain conditions\, distinguishing between a standard multivariate Gaussian and a distribution that behaves like $A$ in a random hidden direction and like a standard Gaussian in the orthogonal complement\, is SQ-hard. This required 1) $A$ matches many low-order moments with a standard Gaussian\, and (2) the chi-squared norm of $A$ with respect to the standard Gaussian is finite\, where the chi-squared restriction is needed for technical reasons. In this talk\, we will present the new result that shows the Condition (2) above is indeed not necessary.
URL:https://ifds.info/event/ifds-ideas-forum-double-header/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20240226T123000
DTEND;TZID=America/Chicago:20240226T133000
DTSTAMP:20260529T230944
CREATED:20240318T213825Z
LAST-MODIFIED:20240318T213825Z
UID:2900-1708950600-1708954200@ifds.info
SUMMARY:Prelimit coupling and steady-state convergence of constant-stepsize nonsmooth contractive SA
DESCRIPTION:Speaker: Yixuan Zhang \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nAbstract:  \nMotivated by Q-learning\, we study nonsmooth contractive stochastic approximation (SA) with constant stepsize. We focus on two important classes of dynamics: 1) nonsmooth contractive SA with additive noise\, and 2) synchronous and asynchronous Q-learning\, which features both additive and multiplicative noise. For both dynamics\, we establish weak convergence of the iterates to a stationary limit distribution in Wasserstein distance. Furthermore\, we propose a prelimit coupling technique for establishing steady-state convergence and characterize the limit of the stationary distribution as the stepsize goes to zero. Using this result\, we derive that the asymptotic bias of nonsmooth SA is proportional to the square root of the stepsize\, which stands in sharp contrast to smooth SA. This bias characterization allows for the use of Richardson-Romberg extrapolation for bias reduction in nonsmooth SA.
URL:https://ifds.info/event/prelimit-coupling-and-steady-state-convergence-of-constant-stepsize-nonsmooth-contractive-sa/
LOCATION:WID 1145\, 330 N Orchard Street\, Madison\, WI\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20240219T123000
DTEND;TZID=America/Chicago:20240219T133000
DTSTAMP:20260529T230944
CREATED:20240318T213630Z
LAST-MODIFIED:20240318T213656Z
UID:2897-1708345800-1708349400@ifds.info
SUMMARY:A good score does not lead to a good generative model
DESCRIPTION:Speaker: Sixu Li \nAbstract: Score-based Generative Models (SGMs) is one leading method in generative modeling\, renowned for their ability to generate high-quality samples from complex\, high-dimensional data distributions. The method enjoys empirical success and is supported by rigorous theoretical convergence properties. In particular\, it has been shown that SGMs can generate samples from a distribution that is close to the ground-truth if the underlying score function is learned well\, suggesting the success of SGM as a generative model. We provide a counter-example in this paper. Through the sample complexity argument\, we provide one specific setting where the score function is learned well. Yet\, SGMs in this setting can only output samples that are Gaussian blurring of training data points\, mimicking the effects of kernel density estimation. The finding resonates a series of recent finding that reveal that SGMs can demonstrate strong memorization effect and fail to generate. This is joint with Shi Chen and Qin Li. 
URL:https://ifds.info/event/a-good-score-does-not-lead-to-a-good-generative-model/
LOCATION:WID 1145\, 330 N Orchard Street\, Madison\, WI\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20240212T123000
DTEND;TZID=America/Chicago:20240212T133000
DTSTAMP:20260529T230944
CREATED:20240318T213417Z
LAST-MODIFIED:20240318T213417Z
UID:2894-1707741000-1707744600@ifds.info
SUMMARY:Theoretical exploration of foundation model adaption methods
DESCRIPTION:Speaker: Kangwook Lee
URL:https://ifds.info/event/theoretical-exploration-of-foundation-model-adaption-methods/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20240205T123000
DTEND;TZID=America/Chicago:20240205T133000
DTSTAMP:20260529T230944
CREATED:20240318T213252Z
LAST-MODIFIED:20240318T213252Z
UID:2892-1707136200-1707139800@ifds.info
SUMMARY:Towards a new toolbox of optimal statistical primitives
DESCRIPTION:Abstract: Given society’s increasing reliance on data\, its collection and processing into useful information is a technical problem of growing focus\, and perhaps paradoxically\, a critical bottleneck in many data science and machine learning applications. My research focuses on designing algorithms that push the limits of both statistical efficiency and computational efficiency. In particular\, my work tackles the divide between the theory and practice of data science\, which exists even for the most basic statistical problems including mean and (co)variance estimation. Conventional methods such as the sample mean\, while supported by theoretical results under strong assumptions\, are often brittle in the presence of extreme data points. To counter such deficiencies\, practitioners often use ad-hoc and unprincipled “outlier removal” heuristics\, revealing a marked gap between the theory and practice even for these fundamental problems. \nIn this talk\, I will describe my work towards building a new toolbox of optimal statistical primitives\, bridging the theory-practice divide. I will specifically highlight 3 works: A) constructing a statistically-optimal and computationally-efficient 1-dimensional mean estimator\, whose estimation error is optimal even in the leading multiplicative constant\, under bare minimum distributional assumptions\, B) a rather different but also optimal mean estimator for the “very high-dimensional” regime\, and C) a recent result on robustly clustering Gaussian mixtures based on their covariances even in the presence of adversarial data corruption. To conclude the talk\, I will discuss my vision for the new theory and toolbox\, serving as a blueprint for my long-term future research. \nBio: Jasper Lee is a postdoctoral research associate at the University of Wisconsin-Madison\, mentored by Ilias Diakonikolas in the Department of Computer Sciences\, and also affiliated with the Institute for Foundations of Data Science. He completed his PhD at Brown University\, advised by Paul Valiant. \nHis research interests are broadly in the foundations of data science\, aiming to design practical\, data-efficient and computationally-efficient algorithms for a variety of statistical applications. \nHis work is partially supported by a Croucher Fellowship for Postdoctoral Research.
URL:https://ifds.info/event/towards-a-new-toolbox-of-optimal-statistical-primitives/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231218T123000
DTEND;TZID=America/Chicago:20231218T123000
DTSTAMP:20260529T230944
CREATED:20231024T213157Z
LAST-MODIFIED:20231024T215501Z
UID:2708-1702902600-1702902600@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:TBD\nSpeaker: Sushrut Karmalkar
URL:https://ifds.info/event/tbd-3/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231211T123000
DTEND;TZID=America/Chicago:20231211T123000
DTSTAMP:20260529T230944
CREATED:20231024T213143Z
LAST-MODIFIED:20231024T215415Z
UID:2707-1702297800-1702297800@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:TBD\nSpeaker: Thanasis Pittas
URL:https://ifds.info/event/tbd-2/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231204T123000
DTEND;TZID=America/Chicago:20231204T123000
DTSTAMP:20260529T230944
CREATED:20231024T213142Z
LAST-MODIFIED:20231024T215321Z
UID:2706-1701693000-1701693000@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:TBD\nSpeakers: Jitian Zhao / Zhexuan Liu
URL:https://ifds.info/event/short-talk-exact-title-tbd-4/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231127T123000
DTEND;TZID=America/Chicago:20231127T123000
DTSTAMP:20260529T230944
CREATED:20231024T212227Z
LAST-MODIFIED:20231024T215121Z
UID:2686-1701088200-1701088200@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:TBD\nSpeaker: Zarifis Nikos
URL:https://ifds.info/event/ifds-ideas-forum-47/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231120T123000
DTEND;TZID=America/Chicago:20231120T123000
DTSTAMP:20260529T230944
CREATED:20231024T213142Z
LAST-MODIFIED:20231024T215229Z
UID:2705-1700483400-1700483400@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:TBD\nSpeakers: Karan Srivastava / Chenghui Li
URL:https://ifds.info/event/short-talk-exact-title-tbd-3/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231113T123000
DTEND;TZID=America/Chicago:20231113T123000
DTSTAMP:20260529T230944
CREATED:20231024T213142Z
LAST-MODIFIED:20231024T215011Z
UID:2704-1699878600-1699878600@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:TBD\nSpeakers: William Powell / Andrew Lowy
URL:https://ifds.info/event/short-talk-exact-title-tbd-2/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231106T123000
DTEND;TZID=America/Chicago:20231106T123000
DTSTAMP:20260529T230944
CREATED:20231024T213128Z
LAST-MODIFIED:20231024T214918Z
UID:2703-1699273800-1699273800@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:TBD\nSpeakers: Joe Shenouda/Matthew Zurek
URL:https://ifds.info/event/short-talk-exact-title-tbd/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231030T123000
DTEND;TZID=America/Chicago:20231030T123000
DTSTAMP:20260529T230944
CREATED:20231024T213128Z
LAST-MODIFIED:20231024T214414Z
UID:2702-1698669000-1698669000@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:Human-in-the-Loop Out of Distribution Detection with False Positive Rate Guarantees\nSpeakers: Harit Vishwakarma/Ramya Vinayak
URL:https://ifds.info/event/human-in-the-loop-out-of-distribution-detection-with-false-positive-rate-guarantees/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231023T123000
DTEND;TZID=America/Chicago:20231023T123000
DTSTAMP:20260529T230944
CREATED:20231024T213128Z
LAST-MODIFIED:20231024T214314Z
UID:2701-1698064200-1698064200@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:A Theoretical Analysis of In-context Task Retrieval and Learning/On Squared-Variable Formulations (and LP)\nSpeakers: Ziqian Lin/ Lijun Ding
URL:https://ifds.info/event/a-theoretical-analysis-of-in-context-task-retrieval-and-learning-on-squared-variable-formulations-and-lp/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231016T123000
DTEND;TZID=America/Chicago:20231016T123000
DTSTAMP:20260529T230944
CREATED:20231024T213128Z
LAST-MODIFIED:20231024T214225Z
UID:2700-1697459400-1697459400@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:Stochastic Regularized Majorization-Minimization / Variance Reduction Beyond Minimization\nSpeaker: Hanbaek Lyu / Ahmet Alacaoglu
URL:https://ifds.info/event/stochastic-regularized-majorization-minimization-variance-reduction-beyond-minimization/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231009T123000
DTEND;TZID=America/Chicago:20231009T123000
DTSTAMP:20260529T230944
CREATED:20231024T213127Z
LAST-MODIFIED:20231024T214132Z
UID:2699-1696854600-1696854600@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:Geometry-Aware Adaptation for Pretrained Models\nSpeaker: Nicholas Roberts
URL:https://ifds.info/event/geometry-aware-adaptation-for-pretrained-models/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20231002T123000
DTEND;TZID=America/Chicago:20231002T123000
DTSTAMP:20260529T230944
CREATED:20231024T213125Z
LAST-MODIFIED:20231024T213357Z
UID:2698-1696249800-1696249800@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:Clustered Federated Learning from the Perspective of Interacting Particle System/The Expressive Power of Low-Rank Adaptation\nSpeakers: Sixu Li/Yuchen Zeng
URL:https://ifds.info/event/clustered-federated-learning-from-the-perspective-of-interacting-particle-system-the-expressive-power-of-low-rank-adaptation/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230927T123000
DTEND;TZID=America/Chicago:20230927T123000
DTSTAMP:20260529T230944
CREATED:20231024T213125Z
LAST-MODIFIED:20231024T214758Z
UID:2697-1695817800-1695817800@ifds.info
SUMMARY:SILO
DESCRIPTION:Toward a grand unified theory of accelerations in optimization and machine learning\nSpeaker: Ernest Ryu
URL:https://ifds.info/event/toward-a-grand-unified-theory-of-accelerations-in-optimization-and-machine-learning/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230925T123000
DTEND;TZID=America/Chicago:20230925T123000
DTSTAMP:20260529T230944
CREATED:20231024T213125Z
LAST-MODIFIED:20231024T214719Z
UID:2696-1695645000-1695645000@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:Accelerating optimization over the probability measure space\nSpeaker: Shi Chen
URL:https://ifds.info/event/accelerating-optimization-over-the-probability-measure-space/
LOCATION:Orchard View Room\, 330 N. Orchard Street\, 3rd Floor NE\, Madison\, Wisconsin\, 53715\, United States
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230918T123000
DTEND;TZID=America/Chicago:20230918T123000
DTSTAMP:20260529T230944
CREATED:20231024T213124Z
LAST-MODIFIED:20231024T214633Z
UID:2695-1695040200-1695040200@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:Peer diffusions over uncertain networks\nSpeaker: Alex Hayes
URL:https://ifds.info/event/peer-diffusions-over-uncertain-networks/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230911T123000
DTEND;TZID=America/Chicago:20230911T123000
DTSTAMP:20260529T230944
CREATED:20231024T213124Z
LAST-MODIFIED:20231024T214518Z
UID:2694-1694435400-1694435400@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:The Deceptive Green Flamingos: a thought experiment on the complexities of AI alignment\nSpeakers: Dimitris Papailiopoulos / Nayoung Lee
URL:https://ifds.info/event/the-deceptive-green-flamingos-a-thought-experiment-on-the-complexities-of-ai-alignment/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
ATTACH;FMTTYPE=image/jpeg:https://ifds.info/wp-content/uploads/2023/10/iStock-1415961311.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230508T123000
DTEND;TZID=America/Chicago:20230508T133000
DTSTAMP:20260529T230944
CREATED:20230313T144731Z
LAST-MODIFIED:20230313T145613Z
UID:2459-1683549000-1683552600@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:Current research
URL:https://ifds.info/event/ifds-ideas-forum-34/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230501T123000
DTEND;TZID=America/Chicago:20230501T133000
DTSTAMP:20260529T230944
CREATED:20230313T144731Z
LAST-MODIFIED:20230313T145553Z
UID:2458-1682944200-1682947800@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:
URL:https://ifds.info/event/ifds-ideas-forum-33/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230424T123000
DTEND;TZID=America/Chicago:20230424T133000
DTSTAMP:20260529T230944
CREATED:20230313T144730Z
LAST-MODIFIED:20230313T145529Z
UID:2457-1682339400-1682343000@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:Current research
URL:https://ifds.info/event/ifds-ideas-forum-32/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230417T123000
DTEND;TZID=America/Chicago:20230417T133000
DTSTAMP:20260529T230944
CREATED:20230313T144730Z
LAST-MODIFIED:20230313T145419Z
UID:2456-1681734600-1681738200@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:Current research
URL:https://ifds.info/event/ifds-ideas-forum-31/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230410T123000
DTEND;TZID=America/Chicago:20230410T133000
DTSTAMP:20260529T230944
CREATED:20230313T144730Z
LAST-MODIFIED:20230313T145356Z
UID:2455-1681129800-1681133400@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:Current research
URL:https://ifds.info/event/ifds-ideas-forum-30/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230403T123000
DTEND;TZID=America/Chicago:20230403T133000
DTSTAMP:20260529T230944
CREATED:20230313T144716Z
LAST-MODIFIED:20230313T145334Z
UID:2454-1680525000-1680528600@ifds.info
SUMMARY:IFDS Ideas Forum
DESCRIPTION:Several open problems
URL:https://ifds.info/event/ifds-ideas-forum-29/
LOCATION:WI
CATEGORIES:IFDS Ideas Forum
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20230320T123000
DTEND;TZID=America/Chicago:20230320T133000
DTSTAMP:20260529T230944
CREATED:20230313T144715Z
LAST-MODIFIED:20230313T153516Z
UID:2452-1679315400-1679319000@ifds.info
SUMMARY:IFDS Ideas Forum: Misha Khodak
DESCRIPTION:New Directions in Algorithms with Predictions: Learning and Privacy \n\n\n\n\n\nAbstract: A burgeoning paradigm in algorithm design is learning-augmented algorithms\, or algorithms with predictions\, where methods can take advantage of a (possibly imperfect) prediction about their instance. While past work has focused on using predictions to improve competitive ratios and runtime\, this talk addresses a different\, salient question: how do we learn the predictions themselves? We introduce an approach for co-designing learning-augmented algorithms with their own custom learning algorithms\, with the crucial step being to optimize nice surrogate losses bounding the algorithms’ costs. This leads to improved sample complexity bounds for several learning-augmented graph algorithms and the first learning-theoretic guarantees for page migration with predictions\, among other contributions. We also instantiate these ideas on the new direction of learning-augmented private algorithms\, where the goal is to reduce utility loss due to privacy rather than runtime. Our approach drives numerous insights on how to robustly incorporate external information to release better statistics of sensitive datasets\, which we verify empirically on the task of multiple quantile release.Bio: Misha Khodak is a PhD student in computer science at Carnegie Mellon University advised by Nina Balcan and Ameet Talwalkar. He studies foundations and applications of machine learning\, especially meta-learning and algorithm design. Misha is a recipient of the Facebook PhD Fellowship and has interned at Google Research – New York\, Microsoft Research – New England\, the Lawrence Livermore National Lab\, and the Princeton Plasma Physics Lab.
URL:https://ifds.info/event/ifds-ideas-forum-27/
LOCATION:CS 1240
CATEGORIES:IFDS Ideas Forum
END:VEVENT
END:VCALENDAR