29 citations · 88 across the 14 of their papers we have counts for
14 papers
When Should We Orchestrate Multiple Agents?
Umang Bhatt, Sanyam Kapoor, Mihir Upadhyay +6
Strategies for orchestrating the interactions between multiple agents, both human and artificial, can wildly overestimate performance and underestimate the cost of orchestration. W…
Large Language Models Must Be Taught to Know What They Don't Know
Sanyam Kapoor, Nate Gruver, Manley Roberts +7
When using large language models (LLMs) in high-stakes applications, we need to know when we can trust their predictions. Some works argue that prompting high-performance LLMs is s…
Function-Space Regularization in Neural Networks: A Probabilistic Perspective
Tim G. J. Rudner, Sanyam Kapoor, Shikai Qiu +1
Parameter-space regularization in neural network optimization is a fundamental tool for improving generalization. However, standard parameter-space regularization methods make it c…
Should We Learn Most Likely Functions or Parameters?
Shikai Qiu, Tim G. J. Rudner, Sanyam Kapoor +1
Standard regularized training procedures correspond to maximizing a posterior distribution over parameters, known as maximum a posteriori (MAP) estimation. However, model parameter…
PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
Sanae Lotfi, Marc Finzi, Sanyam Kapoor +3
While there has been progress in developing non-vacuous generalization bounds for deep neural networks, these bounds tend to be uninformative about why deep learning works. In this…
Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
Ravid Shwartz-Ziv, Micah Goldblum, Hossein Souri +4
Deep learning is increasingly moving towards a transfer learning paradigm whereby large foundation models are fine-tuned on downstream tasks, starting from an initialization learne…
On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification
Sanyam Kapoor, Wesley J. Maddox, Pavel Izmailov +1
Aleatoric uncertainty captures the inherent randomness of the data, such as measurement noise. In Bayesian regression, we often use a Gaussian observation model, where we control t…
When are Iterative Gaussian Processes Reliably Accurate?
Wesley J. Maddox, Sanyam Kapoor, Andrew Gordon Wilson
While recent work on conjugate gradient methods and Lanczos decompositions have achieved scalable Gaussian process inference with highly accurate point predictions, in several impl…
A Simple and Fast Baseline for Tuning Large XGBoost Models
Sanyam Kapoor, Valerio Perrone
XGBoost, a scalable tree boosting algorithm, has proven effective for many prediction tasks of practical interest, especially using tabular datasets. Hyperparameter tuning can furt…
SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
Sanyam Kapoor, Marc Finzi, Ke Alexander Wang +1
State-of-the-art methods for scalable Gaussian processes use iterative algorithms, requiring fast matrix vector multiplies (MVMs) with the covariance kernel. The Structured Kernel…
Variational Auto-Regressive Gaussian Processes for Continual Learning
Sanyam Kapoor, Theofanis Karaletsos, Thang D. Bui
Through sequential construction of posteriors on observing data online, Bayes' theorem provides a natural framework for continual learning. We develop Variational Auto-Regressive G…
First-Order Preconditioning via Hypergradient Descent
Ted Moskovitz, Rui Wang, Janice Lan +4
Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space.These difficulti…
Multi-Agent Reinforcement Learning: A Report on Challenges and Approaches
Sanyam Kapoor
Reinforcement Learning (RL) is a learning paradigm concerned with learning to control a system so as to maximize an objective over the long term. This approach to learning has rece…
Backplay: "Man muss immer umkehren"
Cinjon Resnick, Roberta Raileanu, Sanyam Kapoor +3
Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the…