24 citations · 51 across the 32 of their papers we have counts for
37 papers
Learning-Enabled Estimation: Tight Characterizations under Sample Selection Biases
Vikram Kher, Jane H. Lee, Anay Mehrotra +1
When can we learn from biased samples? We study regression when outcomes are observed only after passing through selection filters that depend on both covariates and outcomes thems…
Optimal Rates for Learning with Monotone Adversaries
Anay Mehrotra
A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice, every one of them labeled correctly by the target hypothesis.…
Surprises in Proper Positive-Only Learning
Shai Ben-David, Farnam Mansouri, Anay Mehrotra +1
Binary classification from positive-only samples is a variant of PAC learning in which the learner receives i.i.d. samples from the positive region of an unknown target concept, bu…
Reasoning with Sampling: Cutting at Decision Points
Felix Zhou, Anay Mehrotra, Quanquan C. Liu
Frontier reasoning models are produced by post-training base language models with reinforcement learning. Recent work has challenged this by showing that sampling from a sharpened…
On Language Generation in the Limit with Bounded Memory
Jon Kleinberg, Anay Mehrotra, Amin Saberi +1
We study language generation in the limit under bounded memory. In this task, a learner observes examples from an unknown target language one at a time and must eventually output o…
Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion
Anay Mehrotra, Phuc Tran, Van H. Vu +1
A central goal of modern causal inference is estimating heterogeneous treatment effects to answer questions like "how does an intervention affect each unit," rather than only on av…
What is Learnable in Valiant's Theory of the Learnable?
Steve Hanneke, Anay Mehrotra, Grigoris Velegkas +1
Valiant's 1984 paper is widely credited with introducing the PAC learning model, but it, in fact, introduced a different model: unlike PAC learning, the learner receives only posit…
A Note on Non-Negative -Approximating Polynomials
Jane H. Lee, Anay Mehrotra, Manolis Zampetakis
-Approximating polynomials, i.e., polynomials that approximate indicator functions in -norm under certain distributions, are widely used in computational learning theory.…
Differentially Private Language Generation and Identification in the Limit
Anay Mehrotra, Grigoris Velegkas, Xifan Yu +1
We initiate the study of language generation in the limit, a model recently introduced by Kleinberg and Mullainathan [KM24], under the constraint of differential privacy. We consid…
Mean Estimation from Coarse Data: Characterizations and Efficient Algorithms
Alkis Kalavasis, Anay Mehrotra, Manolis Zampetakis +2
Coarse data arise when learners observe only partial information about samples; namely, a set containing the sample rather than its exact value. This occurs naturally through measu…
Linear Regression with Unknown Truncation Beyond Gaussian Features
Alexandros Kouridakis, Anay Mehrotra, Alkis Kalavasis +1
In truncated linear regression, samples are shown only when the outcome falls inside a certain survival set and the goal is to estimate the unknown -dimens…
Language Generation with Infinite Contamination
Anay Mehrotra, Grigoris Velegkas, Xifan Yu +1
We study language generation in the limit, where an algorithm observes an adversarial enumeration of strings from an unknown target language and must eventually generate new, u…
What Makes Treatment Effects Identifiable? Characterizations and Estimators Beyond Unconfoundedness
Yang Cai, Alkis Kalavasis, Katerina Mamali +2
Most of the widely used estimators of the average treatment effect (ATE) in causal inference rely on the assumptions of unconfoundedness and overlap. Unconfoundedness requires that…
On Union-Closedness of Language Generation
Steve Hanneke, Amin Karbasi, Anay Mehrotra +1
We investigate language generation in the limit - a model by Kleinberg and Mullainathan [NeurIPS 2024] and extended by Li, Raman, and Tewari [COLT 2025]. While Kleinberg and Mullai…
Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases
Alkis Kalavasis, Anay Mehrotra, Felix Zhou
We revisit the problem of estimating linear regressors with self-selection bias in dimensions with the maximum selection criterion, as introduced by Cherapanamjeri, Daskala…
Smoothed Analysis of Learning from Positive Samples
Jane H. Lee, Anay Mehrotra, Manolis Zampetakis
Binary classification from positive-only samples is a variant of PAC learning where the learner receives i.i.d. positive samples and aims to learn a classifier with low error. Prev…
DDPM Score Matching and Distribution Learning
Sinho Chewi, Alkis Kalavasis, Anay Mehrotra +1
Score estimation is the backbone of score-based generative models (SGMs), especially denoising diffusion probabilistic models (DDPMs). A key result in this area shows that with acc…
On Characterizations for Language Generation: Interplay of Hallucinations, Breadth, and Stability
Alkis Kalavasis, Anay Mehrotra, Grigoris Velegkas
We study language generation in the limit - introduced by Kleinberg and Mullainathan [KM24] - building on classical works of Gold [Gol67] and Angluin [Ang79]. [KM24]'s main result…
On the Limits of Language Generation: Trade-Offs Between Hallucination and Mode Collapse
Alkis Kalavasis, Anay Mehrotra, Grigoris Velegkas
Specifying all desirable properties of a language model is challenging, but certain requirements seem essential. Given samples from an unknown language, the trained model should pr…
Smaller Confidence Intervals From IPW Estimators via Data-Dependent Coarsening
Alkis Kalavasis, Anay Mehrotra, Manolis Zampetakis
Inverse propensity-score weighted (IPW) estimators are prevalent in causal inference for estimating average treatment effects in observational studies. Under unconfoundedness, give…
Efficient Statistics With Unknown Truncation, Polynomial Time Algorithms, Beyond Gaussians
Jane H. Lee, Anay Mehrotra, Manolis Zampetakis
We study the estimation of distributional parameters when samples are shown only if they fall in some unknown set . Kontonis, Tzamos, and Zampetakis (FOCS…
Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach
Vijay Keswani, Anay Mehrotra, L. Elisa Celis
In many predictive contexts (e.g., credit lending), true outcomes are only observed for samples that were positively classified in the past. These past observations, in turn, form…
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
Anay Mehrotra, Manolis Zampetakis, Paul Kassianik +4
While Large Language Models (LLMs) display versatile functionality, they continue to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human-designe…
Bias in Evaluation Processes: An Optimization-Based Model
L. Elisa Celis, Amit Kumar, Anay Mehrotra +1
Biases with respect to socially-salient attributes of individuals have been well documented in evaluation processes used in settings such as admissions and hiring. We view such an…