- talks - lists.cs.princeton.edu

UPDATE: Tianyu Gao will present his General Exam "SimCSE: Simple Contrastive Learning of Sentence Embeddings" on Wednesday, April 13, 2022 at 3:00 PM in CS 402 and via Zoom.
by Louis Riehl 11 Apr '22

11 Apr '22

Tianyu Gao will present his General Exam "SimCSE: Simple Contrastive Learning of Sentence Embeddings" on Wednesday, April 13, 2022 at 3:00 PM in CS 402 and via Zoom. Zoom link: 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_rAp4MK0fo05EeL9enjoyep 0Og/edit?usp=sharing 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

Ilya Chugunov will present his General Exam "Implicit Inverse Imaging with Explicit Priors" on Monday, April 18, 2022 at 10 am in Friend Center 202 and via Zoom.
by Louis W. Riehl 11 Apr '22

11 Apr '22

Ilya Chugunov will present his General Exam "Implicit Inverse Imaging with Explicit Priors" on Monday, April 18, 2022 at 10 am in Friend Center 202 and via Zoom. Zoom link: [ https://princeton.zoom.us/j/91472663309 | https://princeton.zoom.us/j/91472663309 ] Committee Members: Felix Heide (advisor), Szymon Rusinkiewicz, Jia Deng Abstract: Armed with the right math, we can solve many tough imaging problems analytically, with no train time and no train data. Unfortunately, from lens aberrations to high level semantic features, the real visual world is full of things we either can’t or don’t want to model, but which we can learn from data. After all, we’ve yet to mathematically define a dog, but even a simple U-Net can be trained to recognize one. In this exam I present three works which try to combine analytic priors with a learned reconstruction pipeline: Mask-ToF, which uses differentiable simulation of time-of-flight imaging to help learn a physical augmentation to depth camera hardware in order to reduce imaging artifacts; GHz-ToF, which uses this same simulation to train a network for correction ambiguity in phase measurements; and my most recent work on handheld neural depth refinement, wherein we train an implicit model to recover fine depth of tabletop objects from a single smartphone camera snapshot. Reading List: [ https://docs.google.com/document/d/1tLs9TnnLzUGX6ebPPVpXsvLgsiCirsKl2Jxo_ji… | https://docs.google.com/document/d/1tLs9TnnLzUGX6ebPPVpXsvLgsiCirsKl2Jxo_ji… ] 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

Thomas Macrina will present his Pre-FPO "Precise Alignment of Serial Section Electron Microscopy Images and Analysis of Neural Circuits" on Tuesday, April 12, 2022 at 5 pm EDT via Zoom.
by Louis W. Riehl 08 Apr '22

08 Apr '22

Thomas Macrina will present his Pre-FPO "Precise Alignment of Serial Section Electron Microscopy Images and Analysis of Neural Circuits" on Tuesday, April 12, 2022 at 5 pm EDT via Zoom. Zoom link: https://princeton.zoom.us/j/99057082150 Committee Members: H. Sebastian Seung(Examiner, advisor), Mala Murthy (Examiner), Felix Heide(examiner), Kai Li (reader), Stephan Saalfeld (HHMI Janelia, reader). All are welcome to attend. Title: Precise Alignment of Serial Section Electron Microscopy Images and Analysis of Neural Circuits Abstract: Neural circuits provide a means to test how the structure of a brain is related to its function, but reconstructing complete circuits in awhile mammalian brain is currently not possible. A promising path is to image a brain with serial section electron microscopy and use automatic methods tore construct circuits from the data. The imaging process introduces significant physical distortion that causes the automatic methods to make errors, so it's crucial to remove the distortion in a step called alignment. There are existing approaches to alignment, and by augmenting them with human-in-the-loop intervention we were able to produce a very accurate alignment of a five teravoxel mouse cortex dataset. This approach failed to correct distortion caused by cracks and folds, and the amount of human effort involved made it prohibitively expensive to process larger datasets. To overcome these limitations, our group developed new alignment pipeline that uses deep optic flow models to predict more precise distortion measurements. Using this new alignment pipeline, we have been able to accurately align much larger datasets, including a 100 teravoxel whole fly brain and a one petavoxel cubic millimeter of mouse cortex. These alignments enabled high quality automatic reconstructions that are now being proofread with manageable human effort to produce some of the largest neural circuits to date. With improvements in the reconstruction technology, like our new alignment pipeline, neural circuits are becoming more accessible, and there will be more effort put toward analyzing them. We analyzed a neural circuit reconstructed from the terascale mouse cortex dataset, finding that sizes of synapses in a shared layer 2/3 pyramidal neuron connection have a correlated binary component, and that the network of these pyramidal neurons is well-described by a configuration model. Both results may have implications for how to constrain biological models of memory or neural network organization. Louis Riehl Graduate Administrator Computer Science Department, CS213 Princeton University (609) 258-8014

1 0

Robotics Seminar: Cameron Aubin TODAY at 10:45am
by Emily C. Lawrence 07 Apr '22

07 Apr '22

ROBOTICS SEMINAR Speaker: Cameron Aubin Title: Towards enduring autonomous robots via embodied energy Day: Thursday, April 7, 2022 Time: 10:45-11:45am Location: Friend Center Convocation Room (FC113) Host: Glaucio Paulino Abstract: Modern robots lack the combination of endurance and adaptability that we see in living organisms. One explanation for this phenomenon is that robots are typically composed of individual power, actuation, sensory, and control blocks, each existing as separate materials and optimized for different tasks. Conversely, biological systems are highly interconnected, hierarchical, and capable of self-assembly, thereby enabling increased complexity and multifunctionality. Many robots also house energy in a single storage unit, often a battery, while more advanced organisms distribute energy throughout their entire bodies. In this talk, I will discuss my work developing robots with multifunctional embodied energy systems that increase their performance and endurance. My discussion will focus on the creation of an untethered soft robotic fish containing a “synthetic vascular system” inspired by redox flow batteries. This system combines the functions of mechanical actuation with hydraulic force transfer and electrolyte-based energy storage, increasing the energy density of the robot by over 300%. Next, I will discuss how energy-dense chemical fuels can be used to create powerful (Pstroke > 50W, Pspec = 147W/g) soft microactuators. We have leveraged microscale combustion and localized flame quenching to develop two demonstrations: a soft haptic display that operates at high frequencies (ƒ > 1kHz) without electromechanical valves and a quadrupedal microrobot capable of multigait/directional movement. Using energy-dense fuels at this scale can increase operating time, power density, and ultimately untether microrobotic systems. Bio: Cameron is a PhD candidate in the Department of Mechanical and Aerospace Engineering at Cornell University. He is a member of the Organic Robotics Laboratory and is advised by Dr. Robert Shepherd. Cameron’s work centers on improving the endurance, adaptability, and autonomy of robots by embodying them with multifunctional, biologically-inspired energy systems. His interests also include soft robotics, advanced manufacturing, and microrobotics. Cameron earned a B.S.E in Biomedical Engineering from Duke University in 2014 and an M.S. in Mechanical Engineering from Cornell University in 2019. His is a recipient of the Harriet Davis Fellowship and his research has been featured in several popular media outlets, including CNN, PBS, BBC, Wired, and more.

1 0

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