Search Results for author:
Found 15 papers, 0 papers with code
On the Computational Landscape of Replicable Learning
To obtain this result, we design a replicable lifting framework inspired by Blanc, Lange, Malik, and Tan [2023] that transforms in a black-box manner efficient replicable PAC learners under the uniform marginal distribution over the Boolean hypercube to replicable PAC learners under any marginal distribution, with sample and time complexity that depends on a certain measure of the complexity of the distribution.
Transfer Learning Beyond Bounded Density Ratios
We also provide a discrete analogue of our transfer inequality on the Boolean Hypercube $\{-1, 1\}^n$, and study its connections with the recent problem of Generalization on the Unseen of Abbe, Bengio, Lotfi and Rizk (ICML, 2023).
Replicable Learning of Large-Margin Halfspaces
Departing from the requirement of polynomial time algorithms, using the DP-to-Replicability reduction of Bun, Gaboardi, Hopkins, Impagliazzo, Lei, Pitassi, Sorrell, and Sivakumar [STOC, 2023], we show how to obtain a replicable algorithm for large-margin halfspaces with improved sample complexity with respect to the margin parameter $\tau$, but running time doubly exponential in $1/\tau^2$ and worse sample complexity dependence on $\epsilon$ than one of our previous algorithms.
Learning Hard-Constrained Models with One Sample
For general $H$-colorings, we show that standard conditions that guarantee sampling, such as Dobrushin's condition, are insufficient for one-sample learning; on the positive side, we provide a general condition that is sufficient to guarantee linear-time learning and obtain applications for proper colorings and permissive models.
Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Methods
Deep Neural Networks and Reinforcement Learning methods have empirically shown great promise in tackling challenging combinatorial problems.
Statistical Indistinguishability of Learning Algorithms
When two different parties use the same learning rule on their own data, how can we test whether the distributions of the two outcomes are similar?
Perfect Sampling from Pairwise Comparisons
We design a Markov chain whose stationary distribution coincides with $\mathcal{D}$ and give an algorithm to obtain exact samples using the technique of Coupling from the Past.
Learning and Covering Sums of Independent Random Variables with Unbounded Support
In this work, we address two questions: (i) Are there general families of SIIRVs with unbounded support that can be learned with sample complexity independent of both $n$ and the maximal element of the support?
Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes
Second, we consider the problem of multiclass classification with structured data (such as data lying on a low dimensional manifold or satisfying margin conditions), a setting which is captured by partial concept classes (Alon, Hanneke, Holzman and Moran, FOCS '21).
Replicable Bandits
Similarly, for stochastic linear bandits (with finitely and infinitely many arms) we develop replicable policies that achieve the best-known problem-independent regret bounds with an optimal dependency on the replicability parameter.
Differentially Private Regression with Unbounded Covariates
We provide computationally efficient, differentially private algorithms for the classical regression settings of Least Squares Fitting, Binary Regression and Linear Regression with unbounded covariates.
Label Ranking through Nonparametric Regression
We introduce a generative model for Label Ranking, in noiseless and noisy nonparametric regression settings, and provide sample complexity bounds for learning algorithms in both cases.
Efficient Algorithms for Learning from Coarse Labels
Our main algorithmic result is that essentially any problem learnable from fine grained labels can also be learned efficiently when the coarse data are sufficiently informative.
Aggregating Incomplete and Noisy Rankings
We consider the problem of learning the true ordering of a set of alternatives from largely incomplete and noisy rankings.
Efficient Parameter Estimation of Truncated Boolean Product Distributions
A stunning consequence is that virtually any statistical task (e. g., learning in total variation distance, parameter estimation, uniformity or identity testing) that can be performed efficiently for Boolean product distributions, can also be performed from truncated samples, with a small increase in sample complexity.
