2.3k citations · 2.4k across the 11 of their papers we have counts for
12 papers
High-dimensional estimation with missing data: Statistical and computational limits
Kabir Aladin Verchand, Ankit Pensia, Saminul Haque +1
We consider computationally-efficient estimation of population parameters when observations are subject to missing data. In particular, we consider estimation under the realizable…
Blackbox Model Provenance via Palimpsestic Membership Inference
Rohith Kuditipudi, Jing Huang, Sally Zhu +3
Suppose Alice trains an open-weight language model and Bob uses a blackbox derivative of Alice's model to produce text. Can Alice prove that Bob is using her model, either by query…
Independence Tests for Language Models
Sally Zhu, Ahmed Ahmed, Rohith Kuditipudi +1
We consider the following problem: given the weights of two models, can we test whether they were trained independently -- i.e., from independent random initializations? We conside…
A fast and slightly robust covariance estimator
John Duchi, Saminul Haque, Rohith Kuditipudi
Let from a distribution with mean zero and covariance . Given a dataset $\mathcal…
Auditing Prompt Caching in Language Model APIs
Chenchen Gu, Xiang Lisa Li, Rohith Kuditipudi +2
Prompt caching in large language models (LLMs) results in data-dependent timing variations: cached prompts are processed faster than non-cached prompts. These timing differences in…
Robust Distortion-free Watermarks for Language Models
Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto +1
We propose a methodology for planting watermarks in text from an autoregressive language model that are robust to perturbations without changing the distribution over text up to a…
A Fast Algorithm for Adaptive Private Mean Estimation
John Duchi, Saminul Haque, Rohith Kuditipudi
We design an -differentially private algorithm to estimate the mean of a -variate distribution, with unknown covariance , that is adaptive to . To within…
Memorize to Generalize: on the Necessity of Interpolation in High Dimensional Linear Regression
Chen Cheng, John Duchi, Rohith Kuditipudi
We examine the necessity of interpolation in overparameterized models, that is, when achieving optimal predictive risk in machine learning problems requires (nearly) interpolating…
On the Opportunities and Risks of Foundation Models
Rishi Bommasani, Drew A. Hudson, Ehsan Adeli +111
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.…
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
Rohith Kuditipudi, Xiang Wang, Holden Lee +5
Mode connectivity is a surprising phenomenon in the loss landscape of deep nets. Optima -- at least those discovered by gradient-based optimization -- turn out to be connected by s…
Minimizing the Number of Detrimental Objects in Multi-Dimensional Graph-Based Codes
Ahmed Hareedy, Rohith Kuditipudi, Robert Calderbank
In order to meet the demands of data-hungry applications, data storage devices are required to be increasingly denser. Various sources of error appear with this increase in density…
Learning Two-layer Neural Networks with Symmetric Inputs
Rong Ge, Rohith Kuditipudi, Zhize Li +1
We give a new algorithm for learning a two-layer neural network under a general class of input distributions. Assuming there is a ground-truth two-layer network $$ y = A σ(Wx) + ξ,…