Search Results for author:
Found 18 papers, 6 papers with code
Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models
The recent explosion in the capabilities of large language models has led to a wave of interest in how best to prompt a model to perform a given task.
Distribution-Free Statistical Dispersion Control for Societal Applications
Explicit finite-sample statistical guarantees on model performance are an important ingredient in responsible machine learning.
Stability is Stable: Connections between Replicability, Privacy, and Adaptive Generalization
In particular, we give sample-efficient algorithmic reductions between perfect generalization, approximate differential privacy, and replicability for a broad class of statistical problems.
Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions
In this work, we propose a flexible framework to produce a family of bounds on quantiles of the loss distribution incurred by a predictor.
Learning versus Refutation in Noninteractive Local Differential Privacy
We study two basic statistical tasks in non-interactive local differential privacy (LDP): learning and refutation.
Reproducibility in Learning
We introduce the notion of a reproducible algorithm in the context of learning.
On the Power and Limitations of Branch and Cut
In a recent (and surprising) result, Dadush and Tiwari showed that these short refutations of the Tseitin formulas could be translated into quasi-polynomial size and depth Cutting Planes proofs, refuting a long-standing conjecture.
Computational Complexity
Size and Depth Separation in Approximating Benign Functions with Neural Networks
We show a complexity-theoretic barrier to proving such results beyond size $O(d\log^2(d))$, but also show an explicit benign function, that can be approximated with networks of size $O(d)$ and not with networks of size $o(d/\log d)$.
Theoretical bounds on estimation error for meta-learning
Machine learning models have traditionally been developed under the assumption that the training and test distributions match exactly.
Causal Modeling for Fairness in Dynamical Systems
In many application areas---lending, education, and online recommenders, for example---fairness and equity concerns emerge when a machine learning system interacts with a dynamically changing environment to produce both immediate and long-term effects for individuals and demographic groups.
Flexibly Fair Representation Learning by Disentanglement
We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes.
Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data
Building on prior work in deep learning and generative modeling, we describe how to learn the parameters of this causal model from observational data alone, even in the presence of unobserved confounders.
Learning Adversarially Fair and Transferable Representations
In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream.
Predict Responsibly: Increasing Fairness by Learning to Defer
When machine learning models are used for high-stakes decisions, they should predict accurately, fairly, and responsibly.
Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer
We propose a learning algorithm which accounts for potential biases held by external decision-makers in a system.
Generalization in Adaptive Data Analysis and Holdout Reuse
We also formalize and address the general problem of data reuse in adaptive data analysis.
Preserving Statistical Validity in Adaptive Data Analysis
We show that, surprisingly, there is a way to estimate an exponential in $n$ number of expectations accurately even if the functions are chosen adaptively.
Solving #SAT and Bayesian Inference with Backtracking Search
Furthermore, backtracking's ability to utilize more flexible variable orderings allows us to prove that it can achieve an exponential speedup over other standard algorithms for SUMPROD on some instances.
