BEGIN:VCALENDAR
VERSION:2.0
PRODID:-// - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://tilos.ai
X-WR-CALDESC:Events for 
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:20220313T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20221106T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20230312T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20231105T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20240310T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20241103T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230515T143000
DTEND;TZID=America/Los_Angeles:20230515T153000
DTSTAMP:20260405T213231
CREATED:20250828T202516Z
LAST-MODIFIED:20250828T204126Z
UID:7336-1684161000-1684164600@tilos.ai
SUMMARY:TILOS Seminar: The Hidden Convex Optimization Landscape of Deep Neural Networks
DESCRIPTION:Mert Pilanci\, Stanford University \nAbstract: Since deep neural network training problems are inherently non-convex\, their recent dramatic success largely relies on non-convex optimization heuristics and experimental findings. Despite significant advancements\, the non-convex nature of neural network training poses two central challenges: first\, understanding the underlying mechanisms that contribute to model performance\, and second\, achieving efficient training with low computational cost and energy consumption. The performance of non-convex models is notably influenced by the selection of optimization methods and hyperparameters\, including initialization\, mini-batching\, and step sizes. Conversely\, convex optimization problems are characterized by their robustness to these choices\, allowing for the efficient and consistent achievement of globally optimal solutions\, irrespective of optimization parameters. In this talk\, we explore a novel perspective by examining multilayer neural networks equipped with ReLU activation functions through the framework of convex optimization. We introduce exact convex optimization formulations of ReLU network training problems. We show that two-layer ReLU networks can be globally trained via convex programs with the number of variables polynomial in the number of training samples\, feature dimension\, and the number of hidden neurons. We show that our analysis extends to deeper networks and that these convex programs possess an intuitive geometric interpretation. Our results provide an equivalent characterization of neural networks as convex models where a mixture of locally linear models are fitted to the data with sparsity inducing convex regularization. Moreover\, we show that standard convolutional neural networks can be globally optimized in fully polynomial time. We discuss extensions to batch normalization\, generative adversarial networks and transformers. Finally\, we present numerical simulations verifying our claims and illustrating that the proposed convex approach is faster and more reliable than standard local search heuristics such as SGD and variants. \n\nMert Pilanci is an assistant professor of Electrical Engineering at Stanford University. He received his Ph.D. in Electrical Engineering and Computer Science from UC Berkeley in 2016. Prior to joining Stanford\, he was an assistant professor of Electrical Engineering and Computer Science at the University of Michigan. In 2017\, he was a Math+X postdoctoral fellow working with Emmanuel Candès at Stanford University. Mert’s research interests are in neural networks\, machine learning\, optimization\, and signal processing. His group develops theory and algorithms for solving large scale optimization problems in machine learning. His research also seeks to develop safe and interpretable artificial intelligence and information theoretic foundations of distributed computing.
URL:https://tilos.ai/event/tilos-seminar-the-hidden-convex-optimization-landscape-of-deep-neural-networks/
LOCATION:Virtual
CATEGORIES:TILOS - OPTML++ Seminar Series,TILOS Seminar Series
ATTACH;FMTTYPE=image/jpeg:https://tilos.ai/wp-content/uploads/2023/10/pilanci-mert-e1756408324872.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230519T100000
DTEND;TZID=America/Los_Angeles:20230519T110000
DTSTAMP:20260405T213231
CREATED:20250904T171300Z
LAST-MODIFIED:20250904T171300Z
UID:7337-1684490400-1684494000@tilos.ai
SUMMARY:TILOS Seminar: Learning from Diverse and Small Data
DESCRIPTION:Ramya Korlakai Vinayak\, Assistant Professor\, University of Wisconsin–Madison \nAbstract: Machine learning (ML) algorithms are becoming ubiquitous in various application domains such as public health\, genomics\, psychology\, and social sciences. In these domains\, data is often obtained from populations that are diverse\, e.g.\, varying demographics\, phenotypes\, preferences etc. Many ML algorithms focus on learning model parameters that work well on average over the population but do not capture the diversity. On the other hand\, such datasets usually have few observations per individual that limits our ability to learn about each individual separately. Question of interest in these scenarios is\, how can we reliably capture the diversity in the data in small data settings? \nIn this talk\, we will address this question in the following settings: \n(i) In many applications\, we observe count data which can be modeled as Binomial (e.g.\, polling\, surveys\, epidemiology) or Poisson (e.g.\, single cell RNA data) data. As a single or finite parameters do not capture the diversity of the population in such datasets\, they are often modeled as nonparametric mixtures. In this setting\, we will address the following question\, “how well can we learn the distribution of parameters over the population without learning the individual parameters?” and show that nonparametric maximum likelihood estimators are in fact minimax optimal. \n(ii) Learning preferences from human judgements using comparison queries plays a crucial role in cognitive and behavioral psychology\, crowdsourcing democracy\, surveys in social science applications\, and recommendation systems. 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. We will discuss some recent results on how we can reliably capture diversity in preferences while pooling together data from individuals. \n\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 University of Wisconsin–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 societal data. 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://tilos.ai/event/tilos-seminar-learning-from-diverse-and-small-data/
LOCATION:Virtual
CATEGORIES:TILOS Seminar Series
ATTACH;FMTTYPE=image/jpeg:https://tilos.ai/wp-content/uploads/2025/08/vinayak-ramya-e1711658956146-NwHzUB.jpg
END:VEVENT
END:VCALENDAR