Search Results for author:
Found 25 papers, 3 papers with code
Trading off Consistency and Dimensionality of Convex Surrogates for the Mode
We investigate ways to trade off surrogate loss dimension, the number of problem instances, and restricting the region of consistency in the simplex for multiclass classification.
Forecasting Competitions with Correlated Events
We initiate the study of forecasting competitions for correlated events.
Proper losses for discrete generative models
The characterization rules out a loss whose expectation is the cross-entropy between the target distribution and the model.
An Embedding Framework for the Design and Analysis of Consistent Polyhedral Surrogates
Using these results, we establish that indirect elicitation, a necessary condition for consistency, is also sufficient when working with polyhedral surrogates.
Surrogate Regret Bounds for Polyhedral Losses
Surrogate risk minimization is an ubiquitous paradigm in supervised machine learning, wherein a target problem is solved by minimizing a surrogate loss on a dataset.
Unifying lower bounds on prediction dimension of convex surrogates
The convex consistency dimension of a supervised learning task is the lowest prediction dimension $d$ such that there exists a convex surrogate $L : \mathbb{R}^d \times \mathcal Y \to \mathbb R$ that is consistent for the given task.
Linear Functions to the Extended Reals
This note investigates functions from $\mathbb{R}^d$ to $\mathbb{R} \cup \{\pm \infty\}$ that satisfy axioms of linearity wherever allowed by extended-value arithmetic.
Statistics Theory Computer Science and Game Theory Statistics Theory
Efficient Competitions and Online Learning with Strategic Forecasters
Winner-take-all competitions in forecasting and machine-learning suffer from distorted incentives.
Unifying Lower Bounds on Prediction Dimension of Consistent Convex Surrogates
Given a prediction task, understanding when one can and cannot design a consistent convex surrogate loss, particularly a low-dimensional one, is an important and active area of machine learning research.
Non-parametric Binary regression in metric spaces with KL loss
We propose a non-parametric variant of binary regression, where the hypothesis is regularized to be a Lipschitz function taking a metric space to [0, 1] and the loss is logarithmic.
A Smoothed Analysis of Online Lasso for the Sparse Linear Contextual Bandit Problem
We investigate the sparse linear contextual bandit problem where the parameter $\theta$ is sparse.
An Embedding Framework for Consistent Polyhedral Surrogates
Conversely, we show how to construct a consistent polyhedral surrogate for any given discrete loss.
Decentralized & Collaborative AI on Blockchain
Machine learning has recently enabled large advances in artificial intelligence, but these tend to be highly centralized.
Toward a Characterization of Loss Functions for Distribution Learning
We aim to understand this fact, taking an axiomatic approach to the design of loss functions for learning distributions.
Equal Opportunity in Online Classification with Partial Feedback
We study an online classification problem with partial feedback in which individuals arrive one at a time from a fixed but unknown distribution, and must be classified as positive or negative.
Multi-Observation Regression
Recent work introduced loss functions which measure the error of a prediction based on multiple simultaneous observations or outcomes.
Local Differential Privacy for Evolving Data
Moreover, existing techniques to mitigate this effect do not apply in the "local model" of differential privacy that these systems use.
A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem
Bandit learning is characterized by the tension between long-term exploration and short-term exploitation.
Accuracy First: Selecting a Differential Privacy Level for Accuracy Constrained ERM
Traditional approaches to differential privacy assume a fixed privacy requirement ε for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint.
Strategic Classification from Revealed Preferences
We study an online linear classification problem, in which the data is generated by strategic agents who manipulate their features in an effort to change the classification outcome.
Multi-Observation Elicitation
We study loss functions that measure the accuracy of a prediction based on multiple data points simultaneously.
Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM
Traditional approaches to differential privacy assume a fixed privacy requirement $\epsilon$ for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint.
A Market Framework for Eliciting Private Data
We propose a mechanism for purchasing information from a sequence of participants. The participants may simply hold data points they wish to sell, or may have more sophisticated information; either way, they are incentivized to participate as long as they believe their data points are representative or their information will improve the mechanism's future prediction on a test set. The mechanism, which draws on the principles of prediction markets, has a bounded budget and minimizes generalization error for Bregman divergence loss functions. We then show how to modify this mechanism to preserve the privacy of participants' information: At any given time, the current prices and predictions of the mechanism reveal almost no information about any one participant, yet in total over all participants, information is accurately aggregated.
Low-Cost Learning via Active Data Procurement
Our results in a sense parallel classic sample complexity guarantees, but with the key resource being money rather than quantity of data: With a budget constraint $B$, we give robust risk (predictive error) bounds on the order of $1/\sqrt{B}$.
$\ell_p$ Testing and Learning of Discrete Distributions
For $p > 1$, we can learn and test with a number of samples that is independent of the support size of the distribution: With an $\ell_p$ tolerance $\epsilon$, $O(\max\{ \sqrt{1/\epsilon^q}, 1/\epsilon^2 \})$ samples suffice for testing uniformity and $O(\max\{ 1/\epsilon^q, 1/\epsilon^2\})$ samples suffice for learning, where $q=p/(p-1)$ is the conjugate of $p$.
