ARMS improves gradient estimation for binary variables using antithetic samples.
problem Estimating gradients for binary variables in discrete latent variable models.
method ARMS uses antithetic samples generated by a copula to estimate gradients more efficiently and unbiasedly.
result ARMS outperforms competing methods in training generative models and optimizing variational bounds.
DisARM improves gradient estimation for binary latent variables.
problem Challenges in training models with discrete latent variables.
method Uses antithetic sampling over continuous augmentation.
result DisARM consistently outperforms ARM and baseline methods in log-likelihood and variance.
New algorithms improve MCMC efficiency for complex distributions.
problem High variance and low effective sample size in MCMC samplers.
method Antithetic Riemannian Manifold and Quantum-Inspired Hamiltonian Monte Carlo.
result Improved effective sample size and variance reduction.
Antithetic noise improves diffusion models' uncertainty quantification.
problem Improving uncertainty quantification in diffusion models.
method Pairing each noise sample with its negation, leading to strong negative correlation.
result Substantially more reliable uncertainty quantification with up to 90% narrower confidence intervals.
Paper uses correlated samples to improve variance in variational inference.
problem High variance in stochastic variational inference.
method Differentiable antithetic sampling to generate correlated samples.
result Effective variance reduction in deep generative model learning.
This paper uses antithetic sampling to reduce variance in stochastic gradient descent.
problem High variance in stochastic gradient descent slows down convergence.
method Antithetic sampling to make gradients negatively correlated.
result The proposed method accelerates convergence in machine learning applications.
New method estimates nested expectations with biased and antithetic sampling.
problem Estimating nested expectations with biased and antithetic sampling.
method Nested multilevel Monte Carlo with biased and antithetic sampling.
result Estimator achieves order ε^(-2) asymptotic cost.
Paper proves strong convergence of Ninomiya-Victoir scheme and proposes an improved multilevel estimator.
problem Strong convergence analysis of Ninomiya-Victoir scheme and optimization of multilevel Monte Carlo estimators.
method Proves strong convergence of order 1/2 for Ninomiya-Victoir scheme and proposes a modified scheme with strong coupling to Giles-Szpruch scheme.
result Improves efficiency of multilevel Monte Carlo estimators by reducing the number of discretization levels.
CARMS improves gradient estimation for categorical variables.
problem Accurately backpropagating gradients through categorical variables.
method CARMS combines REINFORCE with antithetic sampling to create unbiased gradient estimators.
result CARMS outperforms competing methods on various tasks.
New methods extend kernel estimators for partial rankings, improving performance in machine learning tasks.
problem Incomplete rankings data in real-world applications.
method Antithetic and Monte Carlo kernel estimators for partial rankings, variance reduction scheme.
result Improved antithetic kernel estimator with lower variance and better performance.
Improved MLMC method boosts risk estimation efficiency.
problem Estimating risk measures like Value-at-Risk in financial risk management.
method Novel MLMC parametrization and antithetic sampling.
result Significantly improved performance in practical settings.
New algorithm reduces variance in stochastic gradient estimation.
problem Optimizing the variance of stochastic gradient algorithms for non-log-concave distributions.
method Developed a Multi-index Antithetic Stochastic Gradient Algorithm (MASGA) that is independent of the distribution's structure.
result MASGA achieves performance comparable to Monte Carlo estimators with unbiased samples.
This paper uses Monte Carlo simulation to value quality options in agricultural futures contracts.
problem Valuation of quality options in agricultural futures to prevent manipulation and improve hedging performance.
method Monte Carlo simulation with antithetic variables for efficiency.
result Demonstrates a method to estimate the value of quality options in agricultural futures contracts.
A new method improves graph random features with quasi-Monte Carlo techniques.
problem Improving the accuracy of graph random features.
method Induces negative correlations in random walks using antithetic termination.
result Strong theoretical guarantees on lower-variance estimators of the Laplacian kernel.
In this paper we introduce a new multilevel Monte Carlo (MLMC) estimator for multi-dimensional SDEs driven by Brownian motions. Giles has previously shown that if we combine a numerical approximation with strong order of convergence O(Δt) with MLMC we can reduce the computational complexity to estimate expected value…
Framework for sensitivity analysis in biomanufacturing processes.
problem High complexity and uncertainty in biomanufacturing processes.
method Shapley value estimation for linear and nonlinear pKG models, using quasi-Monte Carlo and antithetic sampling.
result Improved efficiency and accuracy in sensitivity analysis for biomanufacturing processes.
Study compares models for pricing multi-strike quanto call options with SV, SC, and SER.
problem Pricing multi-strike quanto call options with stochastic volatility, correlation, and exchange rates.
method Comparative analysis of SV, SC, and SER models; Monte Carlo simulation; Milstein scheme; antithetic variates; correlation risk parameters.
result GARCH-Jump SV, Weibull SC, and Ornstein Uhlenbeck (OU) SER model combination performs best.
Stochastic Variational Optimization is a parallelizable method for gradient estimation.
problem Gradient estimation for differentiable objectives in parallel environments.
method Variational Optimization, Natural Evolution Strategies, Gaussian Perturbation, Directional Derivatives.
result Directional Derivatives are preferable to Variational Optimization for parallel Stochastic Gradient Descent.
ARM estimator improves gradient backpropagation in binary networks.
problem Improving gradient backpropagation through stochastic binary layers.
method ARM estimator using augment-REINFORCE-merge approach.
result ARM estimator achieves state-of-the-art performance in binary models.
Study shows different price correlations in European electricity markets.
problem Stochastic variability and temporal correlation in electricity prices.
method Comparison of Detrended Fluctuation Analysis (DFA) and Kramers--Moyal equation.
result Intraday 15 minutes spot markets show strong negative correlations, unlike other markets.
A new volatility model calibrates SPX & VIX smiles with 6 parameters.
problem Joint calibration of SPX and VIX smiles with a simple model.
method Quintic Ornstein-Uhlenbeck volatility model with polynomial volatility process.
result Remarkable joint fits of SPX-VIX smiles with only 6 parameters.
Gradient-descent-ascent dynamics can exhibit various behaviors in non-convex non-concave games.
problem Gradient-descent-ascent dynamics in non-convex non-concave games can lead to recurrent behavior and spurious equilibria.
method Combines optimization theory, game theory, and dynamical systems.
result Gradient-descent-ascent dynamics can exhibit Poincaré recurrence and converge to spurious equilibria.
The paper improves support recovery guarantees for the group Lasso.
problem Estimating group-sparse signals from noisy measurements.
method Establishes new conditions for accurate group-level support estimation using the group Lasso.
result Allows for nearly as many recoverable nonzero groups as the total number of groups.
Adaptive SAA solves large-scale stochastic linear programs efficiently.
problem Solving large-scale two-stage stochastic linear programs.
method Iterative algorithm with adaptive sample size and warm starts.
result The algorithm converges to the true solution set with a probabilistic guarantee.
New method estimates causal effects of multiple versions of treatment.
problem Ignoring multiple versions of treatment leads to biased causal effect estimates.
method Mixture-of-Experts framework for estimating version-specific causal effects.
result Effective method for estimating causal effects of latent versions.
We construct equivariant and Bott-type Seiberg-Witten Floer homology and cohomology for 3-manifolds, in particular rational homology spheres, and prove their diffeomorphism invariance. We present several versions of the equivariant theory: the singular version, the de Rham version and the Cartan version, with the first…
SAVeD detects dataset versions without metadata, improving accuracy and separation.
problem Difficulty in identifying similar versions of structured datasets.
method Contrastive learning with modified SimCLR pipeline, generating and contrasting augmented table views.
result SAVeD achieves higher accuracy and separation scores on unseen tables.
New versions of the set-valued average value at risk for multivariate risks are introduced by generalizing the well-known certainty equivalent representation to the set-valued case. The first "regulator" version is independent from any market model whereas the second version, called the market extension, takes trading …
The paper establishes isomorphisms and constructs colored versions of Lawrence representations.
problem Understanding isomorphisms and colored versions of Lawrence representations.
method Explicit isomorphisms and construction of colored versions.
result Matrices for colored versions of BKL and Lawrence representations provided.
Abstract: Proves relative versions of group splitting results.
problem Group splittings and invariant sets.
method Relative versions of earlier results about almost invariant sets and splittings of groups.
result Existence and uniqueness of relative versions of algebraic regular neighbourhoods and JSJ decompositions.
New method reduces version space for CNNs, improving active learning performance.
problem Sampling bias in active learning hinders optimal hypothesis finding in neural networks.
method Version space reduction through prior mass reduction and diameter reduction, proposing a new Gibbs-vote disagreement method.
result Diameter-based querying method reduces version space more effectively than prior mass reduction and other methods.
Optimal transport adapted for contaminated probabilities, showing equivalence under specific conditions.
problem Adapting optimal transport for ε-contaminated sets. method Generalized optimal transport problems with lower probabilities, showing equivalence under ε-contaminations. result Monge's and Kantorovich's problems coincide under ε-contaminated sets, but not always. Paper defines new versions of Jones polynomial and Khovanov homology.
problem No specific problem stated; focuses on new definitions.
method Using maps from Gauss diagrams to their variants to define new Jones polynomial and Khovanov homology.
result New versions of Jones polynomial and Khovanov homology behave differently from original ones.
We show that one can skip the skew-symmetry assumption in the definition of Nambu-Poisson brackets. In other words, a n-ary bracket on the algebra of smooth functions which satisfies the Leibniz rule and a n-ary version of the Jacobi identity must be skew-symmetric. A similar result holds for a non-antisymmetric versio…
Paper proves a noncompact version of Gromov's band-width estimate.
problem Proving a precise upper bound for noncompact Riemannian bands.
method Developed a quantitative partitioned manifold index theory.
result Proved a version of Gromov's band-width estimate for noncompact Riemannian bands.
For knots in S^3, the bi-graded hat version of knot Floer homology is defined over Z; however, for a link L in S^3 with #|L|=l>1, there are 2^{l-1} bi-graded hat versions of link Floer homology defined over Z, the multi-graded hat version of link Floer homology is only defined over F_2 from holomorphic considerations, …
The paper gives a systematic study of the approximate versions of three greedy-type algorithms that are widely used in convex optimization. By approximate version we mean the one where some of evaluations are made with an error. Importance of such versions of greedy-type algorithms in convex optimization and in approxi…
Algorithm tackles adaptive discretization in adversarial Lipschitz bandits for dynamic pricing and auctions.
problem Adaptive discretization in adversarial Lipschitz bandits.
method Adversarial Zooming algorithm for adaptive discretization.
result First algorithm for adversarial Lipschitz bandits with instance-dependent regret bounds.
New twisted versions of wild character varieties created.
problem Constructing twisted wild character varieties.
method Creating new versions of wild character varieties.
result Twisted versions of wild character varieties constructed.
A neural network approach for efficient conditional SHAP calculations.
problem Efficiently calculating conditional SHAP values for various models.
method Surrogate neural network approach for conditional SHAP.
result Efficiently calculates conditional SHAP values for neural networks and other regression models.
This paper circulated previously in a draft version. Now, upon general request, it is about time to distribute the more detailed (and much longer) version. The main technical issues revolve around the fine structure of the compactification of the moduli spaces of flow lines and the obstruction bundle technique, with re…
We recall and partially improve four versions of smooth, non-abelian gerbes: Cech cocycles, classifying maps, bundle gerbes, and principal 2-bundles. We prove that all these four versions are equivalent, and so establish new relations between interesting recent developments. Prominent partial results we prove are a bij…
We give a lower estimate of the framing function of knots, and prove a strengthened version of Dehn's lemma conjectured by Greene-Wiest.
Paper tackles musical version matching at segment level using contrastive learning from weakly-labeled data.
problem Match musical versions at the segment level, not just tracks, with weak annotations.
method Proposes contrastive learning from weakly-labeled audio segments, using a new loss variant.
result Breakthrough performance in segment-level evaluation, outperforming state-of-the-art.
BC-Aligner maintains backward compatibility of embeddings after frequent updates.
problem Updating embeddings without requiring consumer teams to retrain their models.
method Learning backward compatible embeddings through BC-Aligner.
result BC-Aligner maintains backward compatibility with existing unintended tasks after multiple model version updates.
A new method simulates a lazy version of a Markov chain for empirical inference.
problem Estimating and testing unknown Markov chains with limited data.
method Simulates an α-lazy version of an unknown Markov chain, making it ergodic.
result The pseudo spectral gap can be applied to non-ergodic Markov chains.
New framed moves extend classical knot theory results.
problem Extending classical knot theory to framed braids.
method Introduced framed versions of L-moves, Hilden, Pure Hilden groups, and framed versions of the Birman theorem.
result Proved a framed version of the Birman theorem for framed links in plat representation.
We propose a version of the volume conjecture that would relate a certain limit of the colored Jones polynomials of a knot to the volume function defined by a representation of the fundamental group of the knot complement to the special linear group of degree two over complex numbers. We also confirm the conjecture for…