arXiv research

The paper extends log-Sobolev inequalities to matrix-valued settings using combinatorial methods.

We give three lower bounds for the Morse index of a constant mean curvature torus in Euclidean 3-space in terms of its spectral genus g. The first two lower bounds grow linearly in g and are stronger for smaller values of g, while the third grows quadratically in g but is weaker for smaller values of g.

This paper improves reinforcement learning policies in a scalable way.

Study finds minimum growth rate for surface solutions.

BCPO optimizes offline RL policies by converting uncertainty into conservative bounds.

Study on identifying most preferred policy in bandits with vector-valued rewards.

Lower bound found for volatility swap in SABR model.

Within the context of traditional life insurance, a model-independent relationship about how the market value of assets is attributed to the best estimate, the value of in-force business and tax is established. This relationship holds true for any portfolio under run-off assumptions and can be used for the validation o…

In this paper, we derive a useful lower bound for the Kullback-Leibler divergence (KL-divergence) based on the Hammersley-Chapman-Robbins bound (HCRB). The HCRB states that the variance of an estimator is bounded from below by the Chi-square divergence and the expectation value of the estimator. By using the relation b…

We consider the problem of learning the optimal action-value function in the discounted-reward Markov decision processes (MDPs). We prove a new PAC bound on the sample-complexity of model-based value iteration algorithm in the presence of the generative model, which indicates that for an MDP with N state-action pairs a…

In this paper we derive an easily computed approximation to European basket call prices for a local volatility jump-diffusion model. We apply the asymptotic expansion method to find the approximate value of the lower bound of European basket call prices. If the local volatility function is time independent then there i…

New theory of sensitivity for unbiased estimators using Wasserstein geometry.

We give the proof of a tight lower bound on the probability that a binomial random variable exceeds its expected value. The inequality plays an important role in a variety of contexts, including the analysis of relative deviation bounds in learning theory and generalization bounds for unbounded loss functions.

The study optimizes polynomial regression for learning under Gaussian distributions.

New research shows exponential lower bounds for planning in MDPs with linearly-realizable optimal action-value functions.

CQL learns conservative Q-functions to improve offline RL performance.

The paper sets lower bounds for a Kirby-Thompson invariant of 4-manifolds.

We estimate risk measures in Markov cost processes with lower and upper bounds.

We use noncommutative localization to construct a chain complex which counts the critical points of a circle-valued Morse function on a manifold, generalizing the Novikov complex. As a consequence we obtain new topological lower bounds on the minimum number of critical points of a circle-valued Morse function within a …

In his work on singularities, expanders and topology of maps, Gromov showed, using isoperimetric inequalities in graded algebras, that every real valued map on the $n$-torus admits a fibre whose homological size is bounded below by some universal constant depending on $n$. He obtained similar estimates for maps with va…

The study finds the maximum spectrum of 3D manifolds with lower scalar curvature.

Sharp lower bound on GHHs' representation power of CPWL functions.

Berry et al. (1997) initiated the development of the infinite arms bandit problem. They derived a regret lower bound of all allocation strategies for Bernoulli rewards with uniform priors, and proposed strategies based on success runs. Bonald and Proutière (2013) proposed a two-target algorithm that achieves the regret…

A new framework estimates policy value robustly against confounders.

For a given knot, we study the minimal number of positive eigenvalues of the double branched cover over spanning surfaces for the knot. The value gives a lower bound for various genera, the dealternating number and the alternation number of knots, and we prove that Batson's bound for the non-orientable 4-genus gives an…

The study finds lower bounds for the warping degree of a knot projection.

The paper introduces a method to learn and apply value envelopes for faster online reinforcement learning.

We introduce a new class of lower bounds on the log partition function of a Markov random field which makes use of a reversed Jensen's inequality. In particular, our method approximates the intractable distribution using a linear combination of spanning trees with negative weights. This technique is a lower-bound count…

Proves SQ lower bounds for learning two-hidden-layer neural networks.

Optimal rank-adaptive matrix estimation from linear measurements.

The Barankin bound is generalized to the vector case in the mean square error sense. Necessary and sufficient conditions are obtained to achieve the lower bound. To obtain the result, a simple finite dimensional real vector valued generalization of the Riesz representation theorem for Hilbert spaces is given. The bound…

TensorPlan shows an exponential lower bound for planning in MDPs with linearly realizable value functions.

We consider the Max $K$-Armed Bandit problem, where a learning agent is faced with several stochastic arms, each a source of i.i.d. rewards of unknown distribution. At each time step the agent chooses an arm, and observes the reward of the obtained sample. Each sample is considered here as a separate item with the rewa…

New method estimates optimal Q-values with better accuracy for specific problems.

New proof shows lower bound for commutator length in RAAGs.

Let G, a subset of O(4), act isometrically on the 3-sphere. In this article we calculate a lower bound for the diameter of the quotient spaces $S^3/G$. We find it to be ${1/2}\arccos(\frac{\tan(\frac{3 π}{10})}{\sqrt3})$, which is exactly the value of the lower bound for diameters of the spherical space forms. In the p…

We study the stochastic multi-armed bandit problem when one knows the value $μ^{(\star)}$ of an optimal arm, as a well as a positive lower bound on the smallest positive gap $Δ$. We propose a new randomized policy that attains a regret {\em uniformly bounded over time} in this setting. We also prove several lower bound…

S. Nelson, M. Orrison, V. Rivera {\cite{S}} modified Kauffman's construction of bracket. Their invariant $Φ^β_X$ takes value in a finite ring $Z_2[t]/(1+t+t^3)$. In this paper, the author generalizes this invariant. The new invariant takes value in a polynomial ring. Furthermore, for a tricolorable link diagram, the au…

The paper improves bounds on knot crossings and tabulates minimal diagrams.

The paper calculates the value of information in high-dimensional decision making.

New methods for evaluating and optimizing policies in offline RL with unobserved confounders.

For a unit vector field on a closed immersed Euclidean hypersurface $M^{2n+1}$, $n\geq 1$, we exhibit a nontrivial lower bound for its energy which depends on the degree of the Gauss map of the immersion. When the hypersurface is the unit sphere $\mathbb{S}^{2n+1}$, immersed with degree one, this lower bound correspond…

We study boundary value problems for the Dirac operator on Riemannian Spin$^c$ manifolds of bounded geometry and with noncompact boundary. This generalizes a part of the theory of boundary value problems by C. Bär and W. Ballmann for complete manifolds with closed boundary. As an application, we derive the lower bound …

Paper proves a new lower bound on calibration error for binary prediction.

Efficiently computes quasiconcave envelope with limited data.

Transductive learning considers a training set of $m$ labeled samples and a test set of $u$ unlabeled samples, with the goal of best labeling that particular test set. Conversely, inductive learning considers a training set of $m$ labeled samples drawn iid from $P(X,Y)$, with the goal of best labeling any future sample…

Study sharpens unlinking number bounds for special alternating links.

The paper sets limits on the accuracy of macroeconomic forecasts based on statistical moments and trade volumes.