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.
New EiV models correct bias in operator learning with noisy data.
problem Bias in operator learning due to noisy independent variables.
method Developed EiV models for MOR-Physics and DeepONet.
result EiV models reduce bias in noisy operator learning.
Paper addresses underestimation bias in double Q-learning, proposing a method to improve learning performance.
problem Underestimation bias in double Q-learning leading to non-optimal fixed points.
method Proposes a simple approach using approximate dynamic programming to bound the target value.
result Significant improvement in learning performance over baseline algorithms in Atari benchmark tasks.
We consider the off-policy evaluation problem in Markov decision processes with function approximation. We propose a generalization of the recently introduced \emph{emphatic temporal differences} (ETD) algorithm \citep{SuttonMW15}, which encompasses the original ETD(λ), as well as several other off-policy evaluation …
Depth uncertainty networks don't improve with bias correction, contrary to expectations.
problem Improving performance in active learning with overparameterised models like NNs.
method Depth uncertainty networks, compared to underparameterised models, show no improvement in performance with bias correction.
result Depth uncertainty networks do not improve with bias correction, unlike underparameterised models.
A method to reduce bias in model-based policy evaluation by shifting operators.
problem Bias in value function computation from noisy estimated models.
method Operator shifting method to reduce the residual norm error.
result The shifting factor is always positive and upper bounded by $1+O\left(1/n
ight)$.
Open problem: Establishing bounds for Cayley-table completion to discover discrete algorithmic axioms.
problem Discovering discrete algorithmic axioms missing in deep learning.
method Cayley-table completion as a testbed for algorithmic complexity minimization.
result Formal exact recovery bounds for Cayley-table completion.
Extended Gauss-Markov theorem for linear estimation with bounded bias.
problem Linear estimation with bounded bias operator.
method Derive optimal estimator formulas for Nuclear and Spectral norms, analyze generalization error.
result Cross-validated Nuclear and Spectral regressors outperform Ridge regression in simulations.
Optimizes learning Hilbert-Schmidt operators between Sobolev spaces.
problem Statistical limits of learning mappings between infinite-dimensional function spaces.
method Minimax optimal regularization and multilevel training.
result Multilevel kernel operator learning achieves optimal learning rate.
Bayesian method corrects bias in imbalanced datasets.
problem Prevalence bias in machine learning datasets.
method Bayesian risk minimization framework, bias-corrected loss function.
result Corrected loss function improves model performance.
Local convolutions bias neural networks towards high-frequency adversarial examples.
problem High-frequency adversarial examples in neural networks.
method Analysis of different linear and nonlinear architectures, focusing on the impact of local convolution operations.
result Local convolutions induce an implicit bias towards high frequency features, leading to high-frequency adversarial examples.
Improved DeepONets for PDE solution operators with adaptive re-weighting and new architecture.
problem Training DeepONets for PDE solution operators without paired data.
method Adaptive re-weighting of training examples and novel network architecture.
result Consistently improved predictive accuracy by a factor of 10-50x.
EBQL reduces bias in Q-learning for improved performance.
problem Over- and under-estimation biases in Q-learning degrade performance.
method Ensemble Bootstrapping to reduce both over- and under-estimation biases.
result EBQL outperforms other Q-learning methods in Atari games.
Core-Halo solves large-scale fixed-point problems by decentralizing updates.
problem Large-scale fixed-point equations with block dependencies.
method Core-Halo decomposition separates write ownership from read-only context, aligning with block-dependence structure.
result Core-Halo achieves near-centralized performance while retaining parallelism.
A novel Q-learning variant reduces underestimation bias in deep actor-critic methods for reinforcement learning.
problem Underestimation bias in deep actor-critic methods for reinforcement learning.
method Introduces a parameter-free Q-learning variant that combines maximum and minimum operators to bound value estimates.
result Improves state-of-the-art performance on OpenAI Gym tasks.
Introduces recency bias to improve time-series forecasting.
problem Lack of recency bias in standard Transformer attention for time-series data.
method Reweights attention scores with a smooth heavy-tailed decay to emphasize nearby observations.
result Recency-biased attention consistently improves sequential modeling and achieves competitive performance on time-series forecasting benchmarks.
This lecture presents recent advances in the theory of errors propagation. We first explain in which cases the propagation of errors may be performed with a first order differential calculus or needs a second order differential calculus. Then we point out the link between error propagation and the concept of second ord…
Receiver operating characteristic (ROC) analysis is widely used for evaluating diagnostic systems. Recent studies have shown that estimating an area under ROC curve (AUC) with standard cross-validation methods suffers from a large bias. The leave-pair-out (LPO) cross-validation has been shown to correct this bias. Howe…
Safe-FinRL uses DRL for high-frequency stock trading, reducing bias and variance.
problem Challenges in applying DRL to high-frequency stock trading, especially bias and variance issues.
method Safe-FinRL separates financial time series into near-stationary short environments and uses Trace-SAC with a general retrace operator.
result Safe-FinRL reduces bias and variance significantly in near-stationary financial environments.
Paper proposes adaptive parameter selection for KGD algorithms.
problem Improving parameter selection for kernel-based gradient descent.
method Integrates bias-variance analysis with splitting method, introduces empirical effective dimension.
result Adaptive parameter selection strategy achieves optimal generalization error bound.
Develops SCMs for latent selection to simplify causal analysis.
problem Latent selection complicates causal analysis.
method Introduces a conditioning operation for SCMs to encode latent selection.
result Conditioning operation preserves simplicity, acyclicity, and linearity of SCMs.
A neural framework corrects bias in estimating individual treatment effects.
problem Estimating individual treatment effects from observational data.
method An anchored neural architecture and precision-corrected intersection-bound inference.
result Corrected bias and maintained nominal coverage in high-dimensional settings.
Paper tackles bias-variance trade-off in missing data, proposing a dynamic framework.
problem Missing data in practical applications deteriorates model performance.
method Develops a fine-grained dynamic learning framework to jointly optimize bias and variance.
result Theoretical and empirical validation of joint bias-variance optimization.
Artificial Intelligence (AI) is an important driving force for the development and transformation of the financial industry. However, with the fast-evolving AI technology and application, unintentional bias, insufficient model validation, immature contingency plan and other underestimated threats may expose the company…
With the purpose of examining biased updates in variance-reduced stochastic gradient methods, we introduce SVAG, a SAG/SAGA-like method with adjustable bias. SVAG is analyzed in a cocoercive root-finding setting, a setting which yields the same results as in the usual smooth convex optimization setting for the ordinary…
New insights into bias-variance tradeoff for data-driven optimization under local misspecification.
problem Understanding the relative performance of SAA, IEO, and ETO under local misspecification.
method Developed a local misspecification perspective using contiguity theory in statistics.
result Explicit expressions for decision bias and geometric understanding of variance.
Graph neural networks improve combinatorial optimization by leveraging inductive bias.
problem Combinatorial optimization problems often arise from related data distributions.
method Using graph neural networks to enhance or solve combinatorial tasks.
result Graph neural networks effectively encode combinatorial and relational input.
Bayesian imputation optimizes bias-variance trade-off in time-series data.
problem Look-ahead bias in imputation of missing time-series data.
method Bayesian consensus posterior that fuses multiple posteriors to optimize bias and variance trade-off.
result Benefit of imputation for portfolio allocation with missing returns demonstrated.
FATE framework attacks graph learning models to amplify bias deceptively.
problem Achieving poisoning attacks on graph learning models to exacerbate bias deceptively.
method Bi-level optimization problem and meta learning-based framework named FATE.
result FATE amplifies bias of graph neural networks while maintaining downstream task utility.
Clip21 improves convergence of gradient-clipped methods in DP settings.
problem Gradient clipping introduces bias in distributed training, causing convergence issues.
method Clip21 designs an error feedback mechanism to mitigate bias in gradient-clipped methods.
result Clip21 converges at the same rate as distributed gradient descent, improving from previous $\mathcal{O}\left(\frac{1}{\sqrt{K}}
ight)$ to $\mathcal{O}\left(\frac{1}{K}
ight)$.
NO approximates non-Markovian BSDEs with polynomial scaling in 1/ε.
problem Complexity of NO approximations for structured families of BSDEs.
method Identifying structured families of non-Markovian BSDEs, informing NO's inductive bias.
result Polynomial scaling in 1/ε for NO approximations of BSDE solution operators.
Deep convolutional networks often append additive constant ("bias") terms to their convolution operations, enabling a richer repertoire of functional mappings. Biases are also used to facilitate training, by subtracting mean response over batches of training images (a component of "batch normalization"). Recent state-o…
Performance of investment managers are evaluated in comparison with benchmarks, such as financial indices. Due to the operational constraint that most professional databases do not track the change of constitution of benchmark portfolios, standard tests of performance suffer from the "look-ahead benchmark bias," when t…
The largest US banks are required by regulatory mandate to estimate the operational risk capital they must hold using an Advanced Measurement Approach (AMA) as defined by the Basel II/III Accords. Most use the Loss Distribution Approach (LDA) which defines the aggregate loss distribution as the convolution of a frequen…
Simplified analysis of SGD for linear regression with weight averaging.
problem Understanding SGD optimization in linear regression models.
method Simplified analysis using linear algebra tools, bypassing complex operator manipulations.
result Recovery of bias and variance bounds for SGD in linear regression.
EMIX minimizes surprise in multi-agent reinforcement learning.
problem Surprise and approximation bias in multi-agent reinforcement learning.
method Energy-based MIXer (EMIX) for minimizing surprise across multiple agents.
result EMIX demonstrates consistent stable performance in challenging StarCraft II scenarios.
New framework assesses value of labeled vs unlabeled data in latent variable models.
problem Determining the optimal use of labeled and unlabeled data in latent variable models.
method Developed a bias-variance decomposition of the generalization error for method-of-moments latent variable estimation, and introduced a correction for misspecification.
result Labeled data is more valuable than unlabeled data when models are misspecified, but this value can be reduced with correction.
Automates neural network design for diverse tasks.
problem Designing neural networks for new, under-explored domains.
method Introduces XD-Operations and a weight-sharing scheme to transform standard backbones into search spaces of operations.
result Models using XD-Operations achieve lower error than baseline and expert-designed networks on diverse tasks.
QFIL improves offline RL by filtering data to reduce bias and variance.
problem Improving offline reinforcement learning policies with limited data.
method QFIL uses a filtered dataset to improve policies, trading off bias and variance through quantile selection.
result QFIL provides a safe policy improvement step with function approximation and effectively balances bias and variance.
Proposes ENOs for learning PDE solutions that conserve energy.
problem Learning dynamics that obey physical laws, especially in super-resolution settings.
method Energy-consistent Neural Operators (ENOs) with a novel penalty function inspired by energy-based theory.
result ENOs outperform existing DNN models in predicting solutions from data, especially in super-resolution settings.
The paper corrects bias in fluid approximation for better decision-making in stochastic optimization.
problem Bias introduced by using mean values in fluid approximation leads to suboptimal decisions.
method Identifying a decision-corrected point estimate that yields optimal decisions.
result A corrected point estimate exists under certain conditions and can be computed algorithmically.
PBC improves AI and dynamical subseasonal forecasts by reducing biases.
problem Subseasonal forecast accuracy drops due to model biases and compounding errors.
method Probabilistic bias correction (PBC) using machine learning to correct historical forecasts.
result PBC doubles AI Forecasting System's subseasonal skill and improves dynamical model skill.
New method reduces sample complexity for robust reinforcement learning.
problem Finite sample analysis in robust reinforcement learning.
method Stochastic approximation framework with controlled bias, using MLMC techniques and geometric truncation.
result Order-optimal sample complexity of ildeO(ε−2) for robust policy evaluation. GCNs improve regression tasks by aggregating neighbor signals.
problem GCNs' statistical properties in regression tasks are poorly understood.
method Examined two GCN convolutions and their impact on learning error.
result GCNs have a bias-variance trade-off that depends on neighborhood size and topology.
SkewSize detects model biases by analyzing mistakes across subgroups.
problem Benchmarking model performance in the presence of spurious correlations.
method Introducing SkewSize, a metric that captures bias from model mistakes.
result SkewSize highlights biases not captured by other metrics.
Improves AUC for disadvantaged groups by adding features.
problem Reducing cross-group differences in AUC for classification models.
method Feature augmentation to improve AUC for disadvantaged groups.
result Significantly improves AUC for disadvantaged groups.
The Whittle likelihood is a widely used and computationally efficient pseudo-likelihood. However, it is known to produce biased parameter estimates for large classes of models. We propose a method for de-biasing Whittle estimates for second-order stationary stochastic processes. The de-biased Whittle likelihood can be …
New method reduces bias in sparse Bayesian learning.
problem High sparsity in statistical models leads to significant bias.
method Variable-coefficient ℓ1 penalty with hyperpriors. result Reduces bias in sparse Bayesian learning.