Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,694 papers · 148 categories

Trend · papers per month

1122 · Jun 202019922001200920172026
24 results for list-decodable

New method for estimating sparse means in noisy data.

problem Estimating the mean of a sparse distribution in the presence of outliers.
method Difference-of-Pairs Filtering technique for list-decodable sparse mean estimation.
result First sample and computationally efficient algorithm for list-decodable sparse mean estimation.

New algorithm for robust mean estimation in high dimensions with nearly-PCA time complexity.

problem Robust mean estimation in high-dimensional data with a minority of contaminated data.
method List-decodable mean estimation algorithm using a novel soft downweighting method, SIFT, and a Ky Fan matrix multiplicative weights procedure.
result Optimal sample complexity and error rate for list-decodable mean estimation with runtime nearly matching PCA.

Polynomial-time algorithm for estimating covariance in corrupted Gaussian data.

problem Estimating covariance in data with up to 1-α fraction of adversarial corruptions.
method Uses low-degree sum-of-squares certificates for anti-concentration and hypercontractivity.
result Outputs a list of candidate parameters with high probability containing a nearly correct covariance.

Boosting improves accuracy with fewer calls to weak learners for certain concept classes.

problem Improving accuracy of learning algorithms with limited weak learner calls.
method Combines boosting and list-decodable codes to achieve better performance for specific concept classes.
result A new boosting algorithm that achieves strong learning with fewer calls to weak learners and additional samples.

We give the first polynomial-time algorithm for robust regression in the list-decodable setting where an adversary can corrupt a greater than 1/21/2 fraction of examples. For any α<1α< 1, our algorithm takes as input a sample {(xi,yi)}in\{(x_i,y_i)\}_{i \leq n} of nn linear equations where αnαn of the equations satisfy $y_i = \l…

2019-05-14abs ↗pdf ↗

A simple model explains phase transition in large language models.

problem Understanding the emergence of abilities in large language models.
method Modeling LLM as a sequence-to-sequence random function and using a list decoder.
result A critical threshold exists where the expected number of erroneous sequences grows exponentially.

New algorithm for batch list-decodable linear regression with stronger guarantees.

problem Efficiently list-decoding linear regression with a fraction of corrupted batches.
method Uses higher-order moments and Sum-of-Squares (SoS) certification to achieve better guarantees.
result Achieves substantially smaller minimum batch size and final error, with optimal list size.

Paper tackles MLR prediction error without assuming realizable models.

problem Prediction error in mixture of linear regressions without realizable assumptions.
method Developed algorithms for list-decoding MLR predictions and minimized empirical risk.
result Alternating minimization algorithm finds best fit lines in non-realizable settings.

Study on list learning with noisy data, showing limits and some learnable cases.

problem Learning from noisy data in a list learning context.
method Inspired by coding theory, extends list learning model to study sparse conjunctions and parities/majors.
result Sparse conjunctions can be efficiently list learned under certain conditions, but parities and majors cannot be efficiently learned.

Proves subgaussian distributions are SoS-certifiably subgaussian, enabling efficient algorithms for various statistical tasks.

problem Efficiently learning from subgaussian distributions in high dimensions.
method Universal constant CC and polynomial sum of squares (SoS) approach.
result Proves subgaussian distributions are SoS-certifiably subgaussian.

Study shows private learning of mixtures of Gaussians is possible with polynomial samples.

problem Estimating mixtures of Gaussians under differential privacy constraints.
method Developed a new framework for privately learning mixtures of Gaussians without structural assumptions.
result Polynomial number of samples (poly(k,d,1/α,1/ε,log(1/δ))) sufficient for estimation up to total variation distance α with (ε, δ)-DP.

This paper bridges outlier-robust estimation in robotics and computer vision with robust statistics.

problem Outlier-robust estimation for geometric perception in robotics and computer vision.
method Adapting and extending robust linear regression and list-decodable regression to non-convex domains and vector-valued measurements.
result Performance guarantees for modern estimation algorithms in the presence of outliers.

Smoothed analysis shows that many classes become learnable from positive-only samples.

problem Learning from positive-only samples is challenging due to negative results in worst-case settings.
method Smoothed analysis of positive-only learning, assuming samples from a reference distribution smooth with respect to the true distribution.
result All VC classes become learnable in the smoothed model with O(VC/ε2)O(VC/ε^2) positive samples for εε classification error.