Labels define the effective timescale for learning from short observations.
problem Learning from short observations with aggregated labels.
method Analytical and Monte Carlo methods to study label variance and effective timescales.
result Labels define the effective timescale for learning, distinguishing architectural from protocol limits.
Sharp bounds derived for minimizing empirical variance.
problem Minimizing empirical variance over functional classes.
method Sharp non-asymptotic bounds derived under mild conditions.
result Fast convergence rates achieved including optimal non-parametric rates.
Empirical study finds variance swap rate is affine in spot variance for S&P500 data.
problem Investigating the relationship between variance swap rate and spot variance.
method Empirical analysis using S&P500 data from 2006-2018, testing different models.
result Affine relationship between variance swap rate and spot variance is supported.
This paper tackles variance issues in GNN training by proposing a method to reduce both embedding and gradient variances.
problem High variance in estimating stochastic gradients in GNN training, especially in large graphs.
method The paper proposes a decoupled variance reduction strategy that employs approximate gradient information to adaptively sample nodes with minimal variance.
result The proposed method achieves faster convergence and better generalization compared to existing sampling methods.
Study shows gradient variance increases during deep learning training, contrary to common belief.
problem Understanding and minimizing gradient variance in deep learning models.
method Gradient Clustering method using stratified sampling to minimize gradient variance.
result Gradient variance increases during training, and smaller learning rates coincide with higher variance.
Sample variance decay is shown in deep ReLU networks, impacting training dynamics.
problem Sample variance decay in deep ReLU networks during training.
method Decomposed total variance into sample variance and network-averaged sum of sample mean and variance.
result Sample variance decays in later layers of deep ReLU networks, impacting training dynamics.
Paper solves a control problem with robust methods.
problem Monotone mean-variance problems with stochastic coefficients.
method Finding saddle point through BSDEs with unbounded coefficients.
result Optimal control and value match mean-variance problems.
The paper analyzes the bias-variance tradeoff for Bregman divergences.
problem Understanding the bias-variance tradeoff for Bregman divergences.
method Analyzes the bias-variance tradeoff through operations in dual space.
result Derives several results including a generalized law of total variance and ensembling operations.
Paper proposes variance reduction for Markov chains, especially useful in MCMC.
problem Reducing variance in Markov chain additive functionals.
method Minimizes asymptotic variance of functionals over control variates.
result Significantly reduces overall finite sample variance in simulations.
Efficient variance estimation for kernel ridge regression.
problem Estimating variance in kernel ridge regression efficiently.
method Random projection approach to estimate variance.
result Optimal variance estimator for various kernels.
Normal distributions ensure asymptotic variance reduction in moment matching Monte Carlo.
problem Asymptotic variance reduction in general integration problems.
method Characterization of conditions for asymptotic variance reduction using normal distributions.
result Asymptotic variance reduction is guaranteed for normal distributions in moment matching Monte Carlo.
A new statistical concept, lepto-variance, is defined for stock returns using Regression Trees.
problem Understanding the underlying structure of stock returns using statistical methods.
method Defining lepto-variance as the variance that cannot be removed by any regression tree of a specific depth and analyzing stock returns with 1- and 2-bit Regression Trees.
result Lepto-variance quantifies the resolving power of Regression Trees for stock returns, decomposing total variance into lepto-variance and macro-variance.
Paper tackles unknown variances in best-arm identification.
problem Identifying the best arm with unknown variances in Gaussian distributions.
method Two approaches: empirical variance plugging or adapting transportation costs.
result The impact of unknown variances is small on sample complexity.
New algorithms improve best-arm identification with varying rewards.
problem Identifying the best arm with varying reward variances in fixed budget.
method Proposed two algorithms: SHVar for known variances, SHAdaVar for unknown variances; uses non-uniform budget allocation.
result Bounding misidentification probabilities for both algorithms.
Study on variance of policy gradient in simple RL environments.
problem Understanding variance of policy gradient estimators in continuous RL.
method Analyzes REINFORCE estimator in linear-quadratic environments with Gaussian noise.
result Derives and validates bounds on estimator variance empirically.
A new measure k-variance captures local distributional shape.
problem Summarizing distributional shape with local information.
method Random bipartite matchings and stochastic approximation.
result Easily approximated k-variance measures capture local distributional properties. Modern neural networks show no bias-variance tradeoff with increased parameters.
problem The traditional bias-variance tradeoff does not hold in over-parameterized neural networks.
method Empirical measurements and theoretical analysis of bias and variance in modern neural networks.
result Bias and variance can decrease as the number of parameters grows in over-parameterized neural networks.
Improved Hamiltonian Monte Carlo for Bayesian inference reduces variance and improves performance.
problem Efficiently sampling from posterior distributions in Bayesian inference with stochastic gradients.
method Variance reduction techniques applied to Hamiltonian Monte Carlo.
result Theoretical and experimental improvements in convergence and performance compared to variance-reduced Langevin dynamics.
A new model minimizes investment risk at multiple time points.
problem Minimizing risk in investment portfolios with multiple stopping points.
method Developed a multi-time state mean-variance model using Riccati equations.
result Optimal investment strategies can be derived from a sequence of Riccati equations.
Increasing variance of losses improves learning with noisy labels.
problem Learning with noisy labels and the need to penalize variance of losses.
method Designing regularizers based on the label noise transition matrix to increase variance of losses.
result Increasing variance of losses significantly improves generalization ability.
New method corrects Markowitz variance for trading volume fluctuations.
problem Incorrect risk estimates from Markowitz variance in trading environments.
method Modeling portfolio variance based on trade volume fluctuations.
result Market-based variance can significantly differ from Markowitz variance.
Neural networks exhibit unimodal variance with model complexity, improving generalization.
problem The classical bias-variance trade-off does not apply to neural networks, leading to better generalization with larger models.
method Measured bias and variance of neural networks, confirmed empirically and theoretically.
result Neural networks show unimodal variance, leading to a double descent risk curve.
This study reviews techniques to estimate volatility and price Variance Swaps.
problem Estimating historical volatility and pricing Variance Swaps.
method Review of existing techniques.
result Discussion of various methods to estimate volatility and price Variance Swaps.
The paper extends a variance gamma model to quadratic functions, reducing arbitrage and computational costs.
problem Creating an arbitrage-free interpolation for option pricing models.
method Generalizing the local variance gamma model to a piecewise quadratic local variance function.
result The quadratic model results in an arbitrage-free interpolation of class C3, reducing knots and computational cost.
New method reduces inference variance for faster optimization.
problem High variance in black-box variational inference.
method Joint control variate addressing both data subsampling and Monte Carlo noise.
result Significantly reduced gradient variance, leading to faster optimization.
This work proposes using zero-variance control variates to reduce variance in pathwise gradient estimators for variational inference.
problem Pathwise gradient estimators in variational inference have high variance, leading to inefficient optimization.
method Apply zero-variance control variates to pathwise gradient estimators.
result Zero-variance control variates can significantly reduce the variance of pathwise gradient estimators without requiring complex assumptions.
UORO reduces gradient variance in online RNN learning.
problem Improving gradient estimates in online RNN learning.
method Analyzes and proposes variance reduction techniques for UORO.
result Reduces gradient variance both theoretically and practically.
VarGrad reduces variance in ELBO gradient estimation for variational inference.
problem Improving the variance of gradient estimators in variational inference.
method VarGrad uses a new log-variance loss to estimate the ELBO gradient, achieving lower variance than the score function method.
result VarGrad offers a lower variance gradient estimator compared to other methods.
A simple method treats heteroscedastic variance variatively, improving model calibration and sample quality.
problem Brittle optimization impacts model likelihoods for mean and variance estimation.
method Proposes a variational approach to heteroscedastic variance, improving predictive mean and variance calibration.
result The proposed method significantly improves parameter calibration and sample quality for regression and VAEs.
Optimizes MCMC chains with neural control variates.
problem Reducing variance in Markov Chain Monte Carlo (MCMC) simulations.
method Uses neural networks as control variates to minimize asymptotic variance.
result Derives optimal convergence rate under various ergodicity assumptions.
Improved LLM pre-training performance through better weight and variance control.
problem Improper weight and variance control in LLM pre-training affects downstream task performance.
method Introduced Layer Index Rescaling (LIR) and Target Variance Rescaling (TVR) techniques.
result Substantial improvements in downstream task performance (up to 4.6%) and reduced extreme activation values.
MFVI can overestimate predictive variance compared to the exact posterior
problem MFVI underestimates posterior variance
method Analyzing conjugate Bayesian Linear Regression
result MFVI can overestimate predictive variance compared to the exact posterior
New algorithms reduce regret in both stochastic and deterministic environments.
problem Designing algorithms that perform well in both types of MDPs.
method Proposed new environment norms and algorithms with variance-dependent regret bounds.
result First algorithm with simultaneously optimal bounds for both stochastic and deterministic MDPs.
Memory-efficient algorithm reduces variance in off-policy RL.
problem High variance in off-policy policy optimization.
method Memory-efficient, stochastically variance-reduced algorithm using off-policy samples.
result Empirically validated effectiveness of the proposed algorithm.
The paper explores the trade-off between bias and variance in high-dimensional models.
problem Understanding the unavoidable trade-off between bias and variance in high-dimensional statistical models.
method Proposes a general strategy to obtain lower bounds on the variance of estimators with a specified bias, and applies it to various statistical models.
result Shows the extent to which the bias-variance trade-off is unavoidable and quantifies the performance loss for methods that do not balance it.
A new QHR model extends HR model with a quadratic variance function.
problem Modeling volatility with greater flexibility and stationarity.
method Introducing a quadratic variance function to the HR model, maintaining Markovian property.
result Stationary distribution of the QHR model is Pearson type IV.
We quantify predictive uncertainty using the posterior predictive variance.
problem Quantifying uncertainty in predictive models.
method Using the law of total variance, we generate expansions for the posterior predictive variance.
result Identify the main contributors to prediction intervals and quantify term-wise uncertainty.
The paper develops a Fourier-based method for optimal hedging in stochastic volatility models.
problem Optimal hedging in financial markets with stochastic volatility.
method Fourier representation in a semimartingale factor model.
result A tractable formula for expected squared hedging error and optimal strategy.
Neural SDEs reduce variance in stochastic simulations.
problem Efficiency of Monte Carlo simulations in finance.
method Use neural SDEs with control variates parameterized by neural networks.
result Prove optimality conditions for variance reduction in SDEs with infinite activity.
NP-PROV separates mean and variance spaces to improve function uncertainty.
problem Neural Processes fail on out-of-domain tasks due to shared latent space uncertainty.
method Separates mean and variance into function-value-related and position-related latent spaces.
result NP-PROV achieves state-of-the-art likelihood with bounded variance in drifts.
Improved regret bounds for contextual bandits considering variance sequences.
problem Establishing lower bounds for contextual bandits with variance-dependent regret.
method Developed variance-dependent lower bounds for linear contextual bandits under two settings: fixed and adaptive variance sequences.
result Lower bounds match upper bounds of SAVE algorithm up to logarithmic factors.
Deep learning models show bias and variance are aligned, not in trade-off.
problem The classical bias-variance trade-off in deep learning models.
method Empirical evidence and theoretical analysis of bias and variance in deep learning models.
result Squared bias is approximately equal to variance for correctly classified sample points in deep learning models.
Large batch sizes reduce gradient variance in DP-SGD, improving privacy.
problem Understanding why large batch sizes work in DP-SGD.
method Decomposed total gradient variance into subsampling and noise-induced variances, proving batch size independence in the limit.
result Large batch sizes reduce effective total gradient variance, improving privacy in DP-SGD.
New formulas derived for variance gamma model option pricing.
problem Option pricing for the variance gamma model.
method Combining randomization method and fractional derivatives.
result Closed-form formulas for European options.
New calibration methods improve fitting of weak variance-alpha-gamma process.
problem Improving fitting of a multivariate Lévy process.
method Comparison of three calibration methods: method of moments, maximum likelihood estimation, and digital moment estimation.
result Maximum likelihood estimation produces a better fit when a specific condition holds, while digital moment estimation produces a better fit when the condition is violated.
Paper improves confidence intervals and variance estimation for deep learning models.
problem Improving confidence intervals and variance estimation in deep learning models.
method Residual-based framework for conditional variance estimation; robust bootstrap procedure for confidence intervals.
result First non-asymptotic bounds for variance estimation using ReLU networks.
Extends Local Variance Gamma model with geometric Brownian motion and piecewise linear local variance.
problem Modeling volatility dynamics in financial markets.
method Develops a geometric version of the Local Variance Gamma model with drift and piecewise linear local variance functions.
result Derives an ordinary differential equation for option prices and solves it in closed form.
The article prices exchange options using variance gamma-like models.
problem Pricing exchange options under specific stochastic processes.
method Derives formulas for variance gamma and variance gamma++ processes, constructs multidimensional versions, calibrates parameters with real data.
result Closed formulas and numerical methods for evaluating exchange options.