97 citations · 369 across the 20 of their papers we have counts for
20 papers
Towards Optimal Estimators for Randomized Control Trials
Harsh Parikh, Gabriel Levin-Konigsberg, Nilesh Tripuraneni +5
Randomized controlled trials (RCTs) are fundamental tools for causal inference across technology companies, pharmaceutical research, and federal agencies. While the standard differ…
Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries
Kiran Vodrahalli, Santiago Ontanon, Nilesh Tripuraneni +21
We introduce Michelangelo: a minimal, synthetic, and unleaked long-context reasoning evaluation for large language models which is also easy to automatically score. This evaluation…
Pretraining Data Mixtures Enable Narrow Model Selection Capabilities in Transformer Models
Steve Yadlowsky, Lyric Doshi, Nilesh Tripuraneni
Transformer models, notably large language models (LLMs), have the remarkable ability to perform in-context learning (ICL) -- to perform new tasks when prompted with unseen input-o…
Choosing a Proxy Metric from Past Experiments
Nilesh Tripuraneni, Lee Richardson, Alexander D'Amour +2
In many randomized experiments, the treatment effect of the long-term metric (i.e. the primary outcome of interest) is often difficult or infeasible to measure. Such long-term metr…
Meta-Analysis of Randomized Experiments with Applications to Heavy-Tailed Response Data
Nilesh Tripuraneni, Dhruv Madeka, Dean Foster +2
A central obstacle in the objective assessment of treatment effect (TE) estimators in randomized control trials (RCTs) is the lack of ground truth (or validation set) to test their…
Covariate Shift in High-Dimensional Random Feature Regression
Nilesh Tripuraneni, Ben Adlam, Jeffrey Pennington
A significant obstacle in the development of robust machine learning models is covariate shift, a form of distribution shift that occurs when the input distributions of the trainin…
Parallelizing Contextual Bandits
Jeffrey Chan, Aldo Pacchiano, Nilesh Tripuraneni +3
Standard approaches to decision-making under uncertainty focus on sequential exploration of the space of decisions. However, \textit{simultaneously} proposing a batch of decisions,…
Optimal Mean Estimation without a Variance
Yeshwanth Cherapanamjeri, Nilesh Tripuraneni, Peter L. Bartlett +1
We study the problem of heavy-tailed mean estimation in settings where the variance of the data-generating distribution does not exist. Concretely, given a sample $\mathbf{X} = \{X…
Optimal Robust Linear Regression in Nearly Linear Time
Yeshwanth Cherapanamjeri, Efe Aras, Nilesh Tripuraneni +3
We study the problem of high-dimensional robust linear regression where a learner is given access to samples from the generative model (with $X…
On the Theory of Transfer Learning: The Importance of Task Diversity
Nilesh Tripuraneni, Michael I. Jordan, Chi Jin
We provide new statistical guarantees for transfer learning via representation learning--when transfer is achieved by learning a feature representation shared across different task…
Provable Meta-Learning of Linear Representations
Nilesh Tripuraneni, Chi Jin, Michael I. Jordan
Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learni…
Algorithms for Heavy-Tailed Statistics: Regression, Covariance Estimation, and Beyond
Yeshwanth Cherapanamjeri, Samuel B. Hopkins, Tarun Kathuria +2
We study efficient algorithms for linear regression and covariance estimation in the absence of Gaussian assumptions on the underlying distributions of samples, making assumptions…
Single Point Transductive Prediction
Nilesh Tripuraneni, Lester Mackey
Standard methods in supervised learning separate training and prediction: the model is fit independently of any test points it may encounter. However, can knowledge of the next tes…
Rao-Blackwellized Stochastic Gradients for Discrete Distributions
Runjing Liu, Jeffrey Regier, Nilesh Tripuraneni +2
We wish to compute the gradient of an expectation over a finite or countably infinite sample space having categories. When is indeed infinite, or finite but ver…
Averaging Stochastic Gradient Descent on Riemannian Manifolds
Nilesh Tripuraneni, Nicolas Flammarion, Francis Bach +1
We consider the minimization of a function defined on a Riemannian manifold accessible only through unbiased estimates of its gradients. We develop a geometric framew…
Stochastic Cubic Regularization for Fast Nonconvex Optimization
Nilesh Tripuraneni, Mitchell Stern, Chi Jin +2
This paper proposes a stochastic variant of a classic algorithm---the cubic-regularized Newton method [Nesterov and Polyak 2006]. The proposed algorithm efficiently escapes saddle…
Lost Relatives of the Gumbel Trick
Matej Balog, Nilesh Tripuraneni, Zoubin Ghahramani +1
The Gumbel trick is a method to sample from a discrete probability distribution, or to estimate its normalizing partition function. The method relies on repeatedly applying a rando…
Magnetic Hamiltonian Monte Carlo
Nilesh Tripuraneni, Mark Rowland, Zoubin Ghahramani +1
Hamiltonian Monte Carlo (HMC) exploits Hamiltonian dynamics to construct efficient proposals for Markov chain Monte Carlo (MCMC). In this paper, we present a generalization of HMC…
A Linear-Time Particle Gibbs Sampler for Infinite Hidden Markov Models
Nilesh Tripuraneni, Shane Gu, Hong Ge +1
Infinite Hidden Markov Models (iHMM's) are an attractive, nonparametric generalization of the classical Hidden Markov Model which can automatically infer the number of hidden state…
Bulk Viscosity and Cavitation in Boost-Invariant Hydrodynamic Expansion
Krishna Rajagopal, Nilesh Tripuraneni
We solve second order relativistic hydrodynamics equations for a boost-invariant 1+1-dimensional expanding fluid with an equation of state taken from lattice calculations of the th…