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.

169,341 papers · 148 categories

Trend · papers per month

0111 · Apr 201419922001200920182026
11 results for disagreement-based

We study agnostic active learning, where the goal is to learn a classifier in a pre-specified hypothesis class interactively with as few label queries as possible, while making no assumptions on the true function generating the labels. The main algorithms for this problem are {\em{disagreement-based active learning}}, …

2014-07-10abs ↗pdf ↗

New algorithm reduces label queries in online learning with bounded errors.

problem Minimizing label queries while limiting prediction errors in streaming data.
method Disagreement-based online learning algorithm for a general hypothesis space under Tsybakov noise.
result The proposed algorithm achieves an optimal label complexity of O(dT22α2αlog2T)O(dT^{\frac{2-2α}{2-α}}\log^2 T) with a matching lower bound.

New algorithms for learning under s-concave distributions, including Pareto and t-distributions.

problem Learning under broad and natural generalizations of log-concave distributions, including fat-tailed ones.
method Introduce new convex geometry tools to study ss-concave distributions and use these properties to provide bounds on learning quantities.
result Significantly generalize prior results for margin-based, disagreement-based, and passive learning of intersections of halfspaces.

Improved active learning for counterfactual learning from observational data.

problem Learning a classifier from observational data with selection bias.
method Active learning with a counterfactual risk minimizer, modifying both risk and active learning process.
result Statistically consistent and more label-efficient algorithm compared to prior work.

New algorithms find the best subset of distributions with minimal samples.

problem Finding the best subset of distributions with minimal samples.
method Design of new algorithms for combinatorial pure exploration in multi-arm bandit framework.
result Achieve new sample-complexity bounds with polynomial improvements.

Study improves resilience against adversarial clean-label attacks in real and noisy settings.

problem Ensuring accurate predictions in the presence of adversarial clean-label samples.
method Sequential learning from a stream of i.i.d. data, allowing abstention for uncertain predictions.
result Theoretical analysis and adaptations for the agnostic setting with a clean-label adversary and noise.

Efficient algorithm for near-optimal online learning with generalized linear functions.

problem Exponential gap between statistically optimal regret and efficient regret for some function classes.
method Computational efficient algorithm for realizable K-wise linear classification and over-parameterized polynomial featurization.
result First algorithm with log(T/σ) regret for realizable K-wise linear classification.

New algorithms improve contextual bandit performance by adapting to problem difficulty.

problem Improving contextual bandit performance on problems with varying difficulty.
method Introducing complexity measures and oracle-efficient algorithms.
result Achieves optimal instance-dependent regret bounds for rich policy classes.