April 2022 - talks - lists.cs.princeton.edu

CS Colloquium speaker Natasha Jaques: TODAY at 12:30pm
by Emily C. Lawrence 07 Apr '22

07 Apr '22

CS Colloquium Speaker Speaker: Natasha Jaques, Google Brain / University of California, Berkeley Date: Thursday, April 7, 2022 Time: 12:30pm EST Location: CS 105 Host: Karthik Narasimhan Event page: [ https://www.cs.princeton.edu/events/26182 | https://www.cs.princeton.edu/events/26182 ] This talk will be live-streamed at [ https://mediacentrallive.princeton.edu/ | https://mediacentrallive.princeton.edu/ ] Title: Social Reinforcement Learning Abstract: Social learning helps humans and animals rapidly adapt to new circumstances, coordinate with others, and drives the emergence of complex learned behaviors. What if it could do the same for AI? This talk describes how Social Reinforcement Learning in multi-agent and human-AI interactions can address fundamental issues in AI such as learning and generalization, while improving social abilities like coordination. I propose a unified method for improving coordination and communication based on causal social influence. I then demonstrate that multi-agent training can be a useful tool for improving learning and generalization. I present PAIRED, in which an adversary learns to construct training environments to maximize regret between a pair of learners, leading to the generation of a complex curriculum of environments. Agents trained with PAIRED generalize more than 20x better to unknown test environments. Ultimately, the goal of my research is to create intelligent agents that can assist humans with everyday tasks; this means leveraging social learning to interact effectively with humans. I show that learning from human social and affective cues scales more effectively than learning from manual feedback. However, it depends on accurate recognition of such cues. Therefore I discuss how to dramatically enhance the accuracy of affect detection models using personalized multi-task learning to account for inter-individual variability. Together, this work argues that Social RL is a valuable approach for developing more general, sophisticated, and cooperative AI, which is ultimately better able to serve human needs. Bio: Natasha Jaques holds a joint position as a Senior Research Scientist at Google Brain and Visiting Postdoctoral Scholar at UC Berkeley. Her research focuses on Social Reinforcement Learning in multi-agent and human-AI interactions. Natasha completed her PhD at MIT, where her thesis received the Outstanding PhD Dissertation Award from the Association for the Advancement of Affective Computing. Her work has also received Best Demo at NeurIPS, an honourable mention for Best Paper at ICML, Best of Collection in the IEEE Transactions on Affective Computing, and Best Paper at the NeurIPS workshops on ML for Healthcare and Cooperative AI. She has interned at DeepMind, Google Brain, and was an OpenAI Scholars mentor. Her work has been featured in Science Magazine, Quartz, IEEE Spectrum, MIT Technology Review, Boston Magazine, and on CBC radio. Natasha earned her Masters degree from the University of British Columbia, and undergraduate degrees in Computer Science and Psychology from the University of Regina.

1 0

Tianyu Gao will present her General Exam "SimCSE: Simple Contrastive Learning of Sentence Embeddings" on Wednesday, April 13, 2022 at 3:00 PM via Zoom.
by Louis W. Riehl 06 Apr '22

06 Apr '22

Tianyu Gao will present her General Exam "SimCSE: Simple Contrastive Learning of Sentence Embeddings" on Wednesday, April 13, 2022 at 3:00 PM via Zoom. Zoom link: [ https://princeton.zoom.us/j/95387462065 | https://princeton.zoom.us/j/95387462065 ] Committee Members: Danqi Chen (advisor), Karthik Narasimhan, Sanjeev Arora Abstract: We present SimCSE, a simple contrastive learning framework that greatly advances the state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrastive objective, with only standard dropout used as noise. This simple method works surprisingly well, performing on par with previous supervised counterparts. We find that dropout acts as minimal data augmentation and removing it leads to a representation collapse. Then, we propose a supervised approach, which incorporates annotated pairs from natural language inference datasets into our contrastive learning framework, by using "entailment" pairs as positives and "contradiction" pairs as hard negatives. We evaluate SimCSE on standard semantic textual similarity (STS) tasks, and our unsupervised and supervised models using BERT base achieve an average of 76.3% and 81.6% Spearman's correlation respectively, a 4.2% and 2.2% improvement compared to previous best results. We also show -- both theoretically and empirically -- that contrastive learning objective regularizes pre-trained embeddings' anisotropic space to be more uniform, and it better aligns positive pairs when supervised signals are available. Reading List: [ https://docs.google.com/document/d/1fSGNfvOSkPggmMZUv_rAp4MK0fo05EeL9enjoye… | https://docs.google.com/document/d/1fSGNfvOSkPggmMZUv_rAp4MK0fo05EeL9enjoye… ] Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so.

1 0

Anat Kleiman will present her MSE talk "Adaptation and Intrinsic Motivations in Reinforcement Learning" on Wednesday, April 13th, 2022 at 2pm via Zoom
by Nicki Mahler 06 Apr '22

06 Apr '22

Anat Kleiman will present her MSE talk "Adaptation and Intrinsic Motivations in Reinforcement Learning" on Wednesday , April 13th, 2022 at 2pm via Zoom. Her committee members are as follows: Ryan Adams (adviser), Karthik Narasimhan (reader) Zoom link: https://princeton.zoom.us/j/92754574624 Please see abstract below. All are welcome to attend. There exist certain discrepancies between how humans and machine learning models learn and make decisions. These discrepancies can not only make it difficult to model human behavior, but can also decrease the efficiency with which models predict and take actions. This thesis will focus on two of these discrepancies, mainly quickly adapting to new tasks using existing knowledge, and the influence of collective, societal goals in individual decision making. It will do this through 2 projects that attempt to provide machine-learning solutions towards allowing for them. The first project focuses on adaptation on the road. By leveraging meta-learning in autonomous vehicle driving, and treating experiences with other drivers as separate tasks, our model learns to generalize knowledge from across different types of drivers. In turn, it is able to quickly adapt to unseen drivers using limited driving experience with them. The second project focuses on collective goal seeking in a multi-agent environment. We use a group intrinsic reward function that is optimized over time to provide agents with an immediate intrinsic reward that they must maximize along with their selfish reward. By using the expected lifetime reward of an agent in the environment to optimize the intrinsic reward function, our agents learn to take possibly sub-optimal actions that benefit the collective group, rather than just themselves.

1 0

Juan Duque will present his MSE Talk "Transformer Representations for Efficient Reinforcement Learning" on Thursday, April 21, 2022 at 3pm via Zoom
by Nicki Mahler 05 Apr '22

05 Apr '22

Juan Duque will present his MSE Talk "Transformer Representations for Efficient Reinforcement Learning" on Thursday, April 21, 2022 at 3pm via zoom. Committee: Karthik Narasimhan (adviser) and Elad Hazan (reader) Zoom link: [ https://princeton.zoom.us/j/93980023607 | https://princeton.zoom.us/j/93980023607 ] All are welcome to attend. Abstract: Reinforcement Learning algorithms are often trained from scratch at high computational costs. In this talk I will present a self-supervised learning framework that uses the Transformer architecture to generate useful representations for Reinforcement Learning. Our formulation uses objectives borrowed from Natural Language Processing and Imitation Learning to pre-train a Tranformer model from offline trajectories that is then fine-tuned on Atari games. We demonstrate how this setup allows for quick online convergence in under 100 thousand episodes.

1 0

CS Colloquium speaker Alex Lombardi: TODAY at 12:30pm
by Emily C. Lawrence 05 Apr '22

05 Apr '22

CS Colloquium Speaker Speaker: Alex Lombardi, Massachusetts Institute of Technology Date: Tuesday, April 5, 2022 Time: 12:30pm EST Location: CS 105 Host: Ran Raz Event page: [ https://www.cs.princeton.edu/events/26181 | https://www.cs.princeton.edu/events/26181 ] This talk will be live-streamed at [ https://mediacentrallive.princeton.edu/ | https://mediacentrallive.princeton.edu/ ] Title: Foundations of Cryptographic Proof Systems Abstract: One of computer science's greatest insights has been in understanding the power and versatility of *proofs*, which were revolutionized in the 1980s to utilize *interaction* as well as other resources such as randomization and computational hardness. Today, they form the backbone of both theoretical and practical cryptography and are simultaneously the source of deep connections to areas such as complexity theory, game theory, and quantum computation. In this talk, I will discuss general-purpose tools, techniques, and abstractions for two key aspects of cryptographic proof systems that have been poorly understood for decades: 1) Can we remove interaction from interactive proofs? Already in the 1980s, Fiat and Shamir proposed a heuristic *but unproven* methodology for removing interaction from interactive proofs, which is now ubiquitous and essential for practical applications. However, it remained open for over 30 years to prove the security of this transformation in essentially any setting of interest. My work on the Fiat-Shamir transform has led to resolutions to many long-standing open problems, including (i) building non-interactive zero knowledge proof systems based on lattice cryptography, (ii) establishing the existence of highly efficient and succinct non-interactive proof systems, and (iii) demonstrating that foundational protocols from the 80s fail to compose in parallel. 2) Are classical interactive protocols secure against quantum computers? At its heart, the problem of analyzing and ruling out quantum attacks on cryptographic protocols is the issue of “rewinding.” The inability to rewind a quantum attack stems from the no-cloning theorem, a fundamental property of quantum information. As a result, very few classical protocols were known to be secure against quantum attacks. In a recent work, I showed how to overcome these difficulties and settle many foundational questions on post-quantum cryptographic proof systems. Our main technique is showing how to efficiently extract certain pieces of (classical) information from a quantum attacker without disturbing its internal state. Bio: Alex Lombardi is a graduate student at MIT advised by Vinod Vaikuntanathan. He is the recipient of an MIT Presidential fellowship, an NDSEG fellowship, and a Charles M. Vest NAE Grand Challenges fellowship. He is broadly interested in cryptography and theoretical computer science with a focus on cryptographic proof systems and post-quantum security.

1 0

QCB Seminar TODAY at 11:00am
by Emily C. Lawrence 04 Apr '22

04 Apr '22

QCB Seminar Nir Yosef, Weizmann Institute of Science Monday, April 4, 2022 11:00 a.m. - 12:00 p.m. (****Please note time!****) Host: Yuri Pritykin Location: Virtual seminar Contact Sara Thibeault at [ mailto:thibeault@princeton.edu | thibeault(a)princeton.edu ] for seminar link “Mapping paths of tumor evolution with single cell phylogenetics” Single-cell genomics provides a powerful set of tools for dissecting temporal processes such as cell differentiation and tumor development from snapshots of asynchronous ensembles of cells. A promising addition to this set of technologies utilizes Cas9- induced mutations as a way of recording lineage information in each cell, thus providing a way to infer the tree (phylogeny) by which individual cells are related. In this talk, I will describe our work on analytical tools for inference of such lineage trees and their joint analysis with the cells’ transcriptomes. I will demonstrate the utility of these tools and the Cas9 lineage tracing system for studying the Kras;Trp53 (KP) mouse model of lung adenocarcinoma, in which progenies of single transformed cells are traced up to the stage of aggressive and metastatic tumors. We will consider different ways by which a concomitant view of cell lineage trees and transcriptomes can be used to shed new light on the trajectories of cell states that are traversed during tumor development, the dynamics and regulation of sub-clonal selection and expansion, and the origins of metastases. Bio: Nir Yosef received his PhD in Computer Science from Tel Aviv University and then completed a postdoctoral training at the Broad Institute, where he worked on transcriptional regulation of T cell differentiation. Nir joined the faculty at UC Berkeley in 2014, where he has most recently served as an Associate Professor of Computer Science and a core member at the Center of Computational Biology. Since January 2022, Nir is an Associate Professor at the Department of Systems Immunology at the Weizmann Institute of Science. The Yosef lab is developing data- centric approaches for studying how changes in transcription are associated with molecular and cellular phenotypes in immunity and cancer. In that capacity, the lab is developing and applying computational tools that leverage single cell genomics, with the goal of better understanding the factors that contribute to variability between cells, (e.g, metabolism, chromatin structure) and their broader implications (e.g., in autoimmunity). A second area of research is studying regulatory regions in the genome, based on chromatin profiles and massively parallel reporter assays.

1 0

CS Colloquium speaker Feras Saad: TODAY at 12:30pm
by Emily C. Lawrence 04 Apr '22

04 Apr '22

Speaker: Feras Saad, Massachusetts Institute of Technology Date: Thursday, March 31, 2022 Time: 12:30pm EST Location: CS 105 Host: Ryan Adams Event page: https://www.cs.princeton.edu/events/26183 This talk will be live-streamed at https://mediacentrallive.princeton.edu/ Title: Scalable Structure Learning and Inference via Probabilistic Programming Abstract: Probabilistic programming supports probabilistic modeling, learning, and inference by representing sophisticated probabilistic models as computer programs in new programming languages. This talk presents efficient probabilistic programming-based techniques that address two fundamental challenges in scaling and automating structure learning and inference over complex data. First, I will describe scalable structure learning methods that make it possible to automatically synthesize probabilistic programs in an online setting by performing Bayesian inference over hierarchies of flexibly structured symbolic program representations, for discovering models of time series data, tabular data, and relational data. Second, I will present fast compilers and symbolic analyses that compute exact answers to a broad range of inference queries about these learned programs, which lets us extract interpretable patterns and make accurate predictions in real time. I will demonstrate how these techniques deliver state-of-the-art performance in terms of runtime, accuracy, robustness, and programmability by drawing on several examples from real-world applications, which include adapting to extreme novelty in economic time series, online forecasting of flu rates given sparse multivariate observations, discovering stochastic motion models of zebrafish hunting, and verifying the fairness of machine learning classifiers. Bio: Feras Saad is a PhD candidate in Computer Science at MIT working at the intersection of programming languages, probabilistic machine learning, and computational statistics. His research is accompanied with a collection of popular open-source probabilistic programming systems used by collaborators at Intel, Takeda, Liberty Mutual, IBM, and the Bill & Melinda Gates Foundation for practical applications of structure learning and probabilistic inference. Feras' MEng thesis on probabilistic programming and data science has been recognized with the 1st Place Computer Science Thesis Award at MIT.

1 1

Sunny Cui will present her MSE Talk "Hierarchical Gaussian Processes and Mixtures of Experts to Model COVID-19 Patient Trajectories" on Friday, April 8th, 2022 11am via Zoom.
by Nicki Mahler 01 Apr '22

01 Apr '22

Sunny Cui will present her MSE Talk " Hierarchical Gaussian Processes and Mixtures of Experts to Model COVID-19 Patient Trajectories" on Friday, April 8th, 2022 11am via Zoom. Zoom link: https://princeton.zoom.us/j/93221657583?pwd=VHVacWZKS3lQNkNCcUNWU2hnbUlldz09 Committee members: Barbara Engelhardt (adviser), Ben Raphael (reader) All are welcome to attend. Hierarchical Gaussian Processes and Mixtures of Experts to Model COVID-19 Patient Trajectories Gaussian processes (GPs) are a versatile nonparametric model for nonlinear regression and have been widely used to study spatiotemporal phenomena. However, standard GPs offer limited interpretability and generalizability for datasets with naturally occurring hierarchies. With large-scale, rapidly-updating electronic health record (EHR) data, we want to study patient trajectories across diverse patient cohorts while preserving patient subgroup structure. In this work, we partition our cohort of over 2000 COVID-19 patients by sex and ethnicity. We develop and apply a hierarchical Gaussian process and a mixture of experts (MOE) hierarchical GP model to fit patient trajectories on clinical markers of disease progression. A case study for albumin, an effective predictor of COVID-19 patient outcomes, highlights the predictive performance of these models. These hierarchical spatiotemporal models of EHR data bring us a step closer toward our goal of building flexible approaches to capture patient data that can be used in real-time systems.

1 0

CS Colloquium Series: week of April 4-8
by Emily C. Lawrence 01 Apr '22

01 Apr '22

Here is the full list of CS Colloquium talks for next week. All talks will be recorded. ~~~~~ CS Colloquium Speaker Speaker: Tej Chajed, Massachusetts Institute of Technology Date: Monday, April 4, 2022 Time: 12:30pm EST Location: CS 105 Host: Amit Levy Event page: https://www.cs.princeton.edu/events/26180 This talk will be live-streamed at https://mediacentrallive.princeton.edu/ Title: Formal verification of a concurrent file system Abstract: Bugs in systems software like file systems, databases, and operating systems can have serious consequences, ranging from security vulnerabilities to data loss, and these bugs affect all the applications built on top. Systems verification is a promising approach to improve the reliability of our computing infrastructure, since it can eliminate whole classes of bugs through machine-checked proofs that show a system always meets its specification. In this talk, I’ll present a line of work culminating in a verified, concurrent file system called DaisyNFS. The file system comes with a proof that shows operations appear to execute correctly and atomically (that is, all-or-nothing), even if the computer crashes and when processing concurrent operations. I’ll describe how a combination of design and verification techniques make it possible to carry out the proof for an efficient implementation. Bio: Tej Chajed is a final-year PhD student at MIT advised by Frans Kaashoek and Nickolai Zeldovich. His research is on systems verification, ranging from developing new foundations through designing and verifying high-performance systems. Before MIT, he completed his undergraduate degree in Electrical Engineering and Computer Science at UIUC. His work has been in part supported by an NSF graduate research fellowship. ~~~~~ CS Colloquium Speaker Speaker: Alex Lombardi, Massachusetts Institute of Technology Date: Tuesday, April 5, 2022 Time: 12:30pm EST Location: CS 105 Host: Ran Raz Event page: https://www.cs.princeton.edu/events/26181 This talk will be live-streamed at https://mediacentrallive.princeton.edu/ Title: Foundations of Cryptographic Proof Systems Abstract: One of computer science's greatest insights has been in understanding the power and versatility of *proofs*, which were revolutionized in the 1980s to utilize *interaction* as well as other resources such as randomization and computational hardness. Today, they form the backbone of both theoretical and practical cryptography and are simultaneously the source of deep connections to areas such as complexity theory, game theory, and quantum computation. In this talk, I will discuss general-purpose tools, techniques, and abstractions for two key aspects of cryptographic proof systems that have been poorly understood for decades: 1) Can we remove interaction from interactive proofs? Already in the 1980s, Fiat and Shamir proposed a heuristic *but unproven* methodology for removing interaction from interactive proofs, which is now ubiquitous and essential for practical applications. However, it remained open for over 30 years to prove the security of this transformation in essentially any setting of interest. My work on the Fiat-Shamir transform has led to resolutions to many long-standing open problems, including (i) building non-interactive zero knowledge proof systems based on lattice cryptography, (ii) establishing the existence of highly efficient and succinct non-interactive proof systems, and (iii) demonstrating that foundational protocols from the 80s fail to compose in parallel. 2) Are classical interactive protocols secure against quantum computers? At its heart, the problem of analyzing and ruling out quantum attacks on cryptographic protocols is the issue of “rewinding.” The inability to rewind a quantum attack stems from the no-cloning theorem, a fundamental property of quantum information. As a result, very few classical protocols were known to be secure against quantum attacks. In a recent work, I showed how to overcome these difficulties and settle many foundational questions on post-quantum cryptographic proof systems. Our main technique is showing how to efficiently extract certain pieces of (classical) information from a quantum attacker without disturbing its internal state. Bio: Alex Lombardi is a graduate student at MIT advised by Vinod Vaikuntanathan. He is the recipient of an MIT Presidential fellowship, an NDSEG fellowship, and a Charles M. Vest NAE Grand Challenges fellowship. He is broadly interested in cryptography and theoretical computer science with a focus on cryptographic proof systems and post-quantum security. ~~~~~ CS Colloquium Speaker Speaker: Natasha Jaques, Google Brain / University of California, Berkeley Date: Thursday, April 7, 2022 Time: 12:30pm EST Location: CS 105 Host: Karthik Narasimhan Event page: https://www.cs.princeton.edu/events/26182 This talk will be live-streamed at https://mediacentrallive.princeton.edu/ Title: Social Reinforcement Learning Abstract: Social learning helps humans and animals rapidly adapt to new circumstances, coordinate with others, and drives the emergence of complex learned behaviors. What if it could do the same for AI? This talk describes how Social Reinforcement Learning in multi-agent and human-AI interactions can address fundamental issues in AI such as learning and generalization, while improving social abilities like coordination. I propose a unified method for improving coordination and communication based on causal social influence. I then demonstrate that multi-agent training can be a useful tool for improving learning and generalization. I present PAIRED, in which an adversary learns to construct training environments to maximize regret between a pair of learners, leading to the generation of a complex curriculum of environments. Agents trained with PAIRED generalize more than 20x better to unknown test environments. Ultimately, the goal of my research is to create intelligent agents that can assist humans with everyday tasks; this means leveraging social learning to interact effectively with humans. I show that learning from human social and affective cues scales more effectively than learning from manual feedback. However, it depends on accurate recognition of such cues. Therefore I discuss how to dramatically enhance the accuracy of affect detection models using personalized multi-task learning to account for inter-individual variability. Together, this work argues that Social RL is a valuable approach for developing more general, sophisticated, and cooperative AI, which is ultimately better able to serve human needs. Bio: Natasha Jaques holds a joint position as a Senior Research Scientist at Google Brain and Visiting Postdoctoral Scholar at UC Berkeley. Her research focuses on Social Reinforcement Learning in multi-agent and human-AI interactions. Natasha completed her PhD at MIT, where her thesis received the Outstanding PhD Dissertation Award from the Association for the Advancement of Affective Computing. Her work has also received Best Demo at NeurIPS, an honourable mention for Best Paper at ICML, Best of Collection in the IEEE Transactions on Affective Computing, and Best Paper at the NeurIPS workshops on ML for Healthcare and Cooperative AI. She has interned at DeepMind, Google Brain, and was an OpenAI Scholars mentor. Her work has been featured in Science Magazine, Quartz, IEEE Spectrum, MIT Technology Review, Boston Magazine, and on CBC radio. Natasha earned her Masters degree from the University of British Columbia, and undergraduate degrees in Computer Science and Psychology from the University of Regina.

1 0