678 citations · 1.6k across the 28 of their papers we have counts for
29 papers
Learning to Evict from Key-Value Cache
Luca Moschella, Laura Manduchi, Ozan Sener
The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache. Existing evi…
Robust Autonomy Emerges from Self-Play
Marco Cusumano-Towner, David Hafner, Alex Hertzberg +9
Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust an…
Leveraging Cardiovascular Simulations for In-Vivo Prediction of Cardiac Biomarkers
Laura Manduchi, Antoine Wehenkel, Jens Behrmann +6
Whole-body hemodynamics simulators, which model blood flow and pressure waveforms as functions of physiological parameters, are now essential tools for studying cardiovascular syst…
Addressing Misspecification in Simulation-based Inference through Data-driven Calibration
Antoine Wehenkel, Juan L. Gamella, Ozan Sener +4
Driven by steady progress in deep generative modeling, simulation-based inference (SBI) has emerged as the workhorse for inferring the parameters of stochastic simulators. However,…
Random Representations Outperform Online Continually Learned Representations
Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru +3
Continual learning has primarily focused on the issue of catastrophic forgetting and the associated stability-plasticity tradeoffs. However, little attention has been paid to the e…
Domain Generalization without Excess Empirical Risk
Ozan Sener, Vladlen Koltun
Given data from diverse sets of distinct distributions, domain generalization aims to learn models that generalize to unseen distributions. A common approach is designing a data-dr…
Generalized Sum Pooling for Metric Learning
Yeti Z. Gurbuz, Ozan Sener, A. Aydın Alatan
A common architectural choice for deep metric learning is a convolutional neural network followed by global average pooling (GAP). Albeit simple, GAP is a highly effective way to a…
Simulation-based Inference for Cardiovascular Models
Antoine Wehenkel, Laura Manduchi, Jens Behrmann +6
Over the past decades, hemodynamics simulators have steadily evolved and have become tools of choice for studying cardiovascular systems in-silico. While such tools are routinely u…
Online Continual Learning Without the Storage Constraint
Ameya Prabhu, Zhipeng Cai, Puneet Dokania +3
Traditional online continual learning (OCL) research has primarily focused on mitigating catastrophic forgetting with fixed and limited storage allocation throughout an agent's lif…
Generalizing Gaussian Smoothing for Random Search
Katelyn Gao, Ozan Sener
Gaussian smoothing (GS) is a derivative-free optimization (DFO) algorithm that estimates the gradient of an objective using perturbations of the current parameters sampled from a s…
Improving information retention in large scale online continual learning
Zhipeng Cai, Vladlen Koltun, Ozan Sener
Given a stream of data sampled from non-stationary distributions, online continual learning (OCL) aims to adapt efficiently to new data while retaining existing knowledge. The typi…
MSeg: A Composite Dataset for Multi-domain Semantic Segmentation
John Lambert, Zhuang Liu, Ozan Sener +2
We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. A naive merge of the constituent datasets yields poor performance due to in…
Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data
Zhipeng Cai, Ozan Sener, Vladlen Koltun
Continual learning is the problem of learning and retaining knowledge through time over multiple tasks and environments. Research has primarily focused on the incremental classific…
Modeling and Optimization Trade-off in Meta-learning
Katelyn Gao, Ozan Sener
By searching for shared inductive biases across tasks, meta-learning promises to accelerate learning on novel tasks, but with the cost of solving a complex bilevel optimization pro…
Drinking from a Firehose: Continual Learning with Web-scale Natural Language
Hexiang Hu, Ozan Sener, Fei Sha +1
Continual learning systems will interact with humans, with each other, and with the physical world through time -- and continue to learn and adapt as they do. An important open pro…
Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks
Umut Şimşekli, Ozan Sener, George Deligiannidis +1
Despite its success in a wide range of applications, characterizing the generalization properties of stochastic gradient descent (SGD) in non-convex deep learning problems is still…
Learning to Guide Random Search
Ozan Sener, Vladlen Koltun
We are interested in derivative-free optimization of high-dimensional functions. The sample complexity of existing methods is high and depends on problem dimensionality, unlike the…
A Stochastic Derivative Free Optimization Method with Momentum
Eduard Gorbunov, Adel Bibi, Ozan Sener +2
We consider the problem of unconstrained minimization of a smooth objective function in in setting where only function evaluations are possible. We propose and analy…
A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control
Adel Bibi, El Houcine Bergou, Ozan Sener +2
We consider the problem of unconstrained minimization of a smooth objective function in in a setting where only function evaluations are possible. While importance sampling…
Multi-Task Learning as Multi-Objective Optimization
Ozan Sener, Vladlen Koltun
In multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them. Multi-task learning is inherently a multi-objective problem because different tasks…
Deep Learning under Privileged Information Using Heteroscedastic Dropout
John Lambert, Ozan Sener, Silvio Savarese
Unlike machines, humans learn through rapid, abstract model-building. The role of a teacher is not simply to hammer home right or wrong answers, but rather to provide intuitive com…
Generalizing to Unseen Domains via Adversarial Data Augmentation
Riccardo Volpi, Hongseok Namkoong, Ozan Sener +3
We are concerned with learning models that generalize well to different \emph{unseen} domains. We consider a worst-case formulation over data distributions that are near the source…
Active Learning for Convolutional Neural Networks: A Core-Set Approach
Ozan Sener, Silvio Savarese
Convolutional neural networks (CNNs) have been successfully applied to many recognition and learning tasks using a universal recipe; training a deep model on a very large dataset o…
Unsupervised Semantic Action Discovery from Video Collections
Ozan Sener, Amir Roshan Zamir, Chenxia Wu +2
Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objectiv…