arXiv research

New online conformal prediction methods minimize strongly adaptive regret and achieve near-optimal coverage.

Optimal online linear regression in dynamic environments using discounted Vovk-Azoury-Warmuth forecaster.

This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least $\sqrt{\log(T)}$ better, where $T$ is the time horizon. Empirical results show tha…

A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments. Recent studies have proposed "meta" algorithms that convert any online learning algorithm to one that is adaptive to changing environments, where the adaptivity is analyzed in a quantity called the strongly-ad…

New proof confirms periodic orbit conjecture for Eulerisable flows.

SA algorithms control dynamic regret in non-stationary settings with strong convexity or exp-concavity.

Given a complex manifold $M$ equipped with a holomorphic action of a connected complex Lie group $G$, and a holomorphic principal $H$--bundle $E_H$ over $X$ equipped with a $G$--connection $h$, we investigate the connections on the principal $H$--bundle $E_H$ that are (strongly) adapted to $h$. Examples are provided by…

Characterizes Anosov flows via contact geometry.

Modified dynamical systems retain Turing universality.

New algorithm reduces TV-denoising to adaptive online learning.

Legendrian arcs connect veering triangulations to Anosov flows.

New approach optimizes policies in adversarial MDPs using adversarial learning.

New algorithms minimize dynamic regret for strongly convex losses.

New algorithms minimize dynamic regret in non-stationary online learning.

New algorithm reduces dynamic regret for exp-concave losses.

Recent work in distance metric learning has focused on learning transformations of data that best align with specified pairwise similarity and dissimilarity constraints, often supplied by a human observer. The learned transformations lead to improved retrieval, classification, and clustering algorithms due to the bette…

Study finds implicit government guarantee improves municipal investment bond ratings.

This paper measures the intensity of implicit government guarantees using PMC index model.

ConfHit provides valid guarantees for generative models without oracle access.

Insurance companies often include very long-term guarantees in participating life insurance products, which can turn out to be very valuable. Under a guaranteed annuity options (G.A.O), the insurer guarantees to convert a policyholder's accumulated funds to a life annuity at a fixed rated when the policy matures. Both …

New model values equity-linked securities with guaranteed return.

Our knowledge about the evolution of guarantee network in downturn period is limited due to the lack of comprehensive data of the whole credit system. Here we analyze the dynamic Chinese guarantee network constructed from a comprehensive bank loan dataset that accounts for nearly 80% total loans in China, during 01/200…

New DP algorithms with margin guarantees for various hypothesis sets.

Two new algorithms recover ridge lines from point clouds with convergence guarantees.

The paper provides theoretical guarantees for optimized sampling in compressed sensing, showing error vanishes with more measurements.

Paper proves robust estimators' generalization guarantees without dimensionality issues.

New algorithms achieve uniform-PAC guarantees for RL with bounded eluder dimension.

New guarantees for adaptive combinatorial maximization with various objectives.

Exact generalization guarantees for robust models using Wasserstein distance are established.

Develops statistical guarantees for neural networks with regularization.

Efficient RNN algorithm guarantees convergence in online learning.

We enhance conformal prediction for risk-averse decisions with action-conditional guarantees.

Improves bandits with knapsacks guarantees for partially stochastic workloads.

The paper proves statistical consistency and fairness guarantees for a plug-in algorithm.

Variable annuities, as a class of retirement income products, allow equity market exposure for a policyholder's retirement fund with electable additional guarantees to limit the downside risk of the market. Management fees and guarantee insurance fees are charged respectively for the market exposure and for the protect…

Optimal liquidation using VWAP strategies has been considered in the literature, though never in the presence of permanent market impact and only rarely with execution costs. Moreover, only VWAP strategies have been studied and the pricing of guaranteed VWAP contracts has never been addressed. In this article, we devel…

Reinsurance can help life insurers maintain higher capital guarantees without losing utility.

Paper provides statistical guarantees for GNNs in link prediction.

New guarantees for black-box variational inference methods.

This paper improves convergence guarantees for gradient clipping in deep learning.

In this paper, we provide local and global convergence guarantees for recovering CP (Candecomp/Parafac) tensor decomposition. The main step of the proposed algorithm is a simple alternating rank-$1$ update which is the alternating version of the tensor power iteration adapted for asymmetric tensors. Local convergence g…

Algorithm learns from both labeled and arbitrary test examples, giving guarantees for bounded VC dimension classes.

Paper provides exponential convergence guarantees for Iterative Markovian Fitting.

Framework for fair classification with noisy protected attributes and provable guarantees.

We provide recovery guarantees for compressible signals that have been corrupted with noise and extend the framework introduced in \cite{bafna2018thwarting} to defend neural networks against $\ell_0$-norm, $\ell_2$-norm, and $\ell_{\infty}$-norm attacks. Our results are general as they can be applied to most unitary tr…

T-SCI improves Cox-MLP's guaranteed coverage for censored data.

We show how to take any two parameter-free online learning algorithms with different regret guarantees and obtain a single algorithm whose regret is the minimum of the two base algorithms. Our method is embarrassingly simple: just add the iterates. This trick can generate efficient algorithms that adapt to many norms s…

Histogram binning method proven with guarantees without splitting data.