New oracles improve stochastic optimization with noisy or biased measurements.
problem Optimizing functions with noisy or biased measurements.
method Introduced biased gradient oracles for stochastic optimization, analyzed RSG and SGD algorithms with these oracles.
result Derived non-asymptotic bounds for convergence rates of algorithms with biased gradient oracles.
Neural networks with learned biases can approximate any function.
problem Whether neural networks with only learned biases can approximate any continuous function.
method Theoretical and numerical analysis of random weights and learned biases in neural networks.
result Feedforward and recurrent neural networks with random weights can approximate any continuous function and dynamical systems.
Analyze SGD with biased gradients, improving convergence rates and accuracy.
problem Analyzing the convergence of SGD with biased gradients.
method Derive convergence results for smooth non-convex functions and quantify the impact of bias magnitude.
result Improved rates under the Polyak-Lojasiewicz condition and insights into how bias magnitude affects accuracy and convergence.
Algorithm improves recommendation subset selection in the presence of biases.
problem Maximizing submodular functions for recommendation in the presence of social biases.
method Algorithm for submodular maximization with fairness constraints.
result Algorithm provably outputs subsets with near-optimal utility and proportional representation.
Neural networks with random hidden nodes have gained increasing interest from researchers and practical applications. This is due to their unique features such as very fast training and universal approximation property. In these networks the weights and biases of hidden nodes determining the nonlinear feature mapping a…
This paper analyzes SGD with biased gradients for deep learning models.
problem Analyzing SGD with biased gradients for deep learning models.
method Non-asymptotic analysis of SGD with adaptive steps for non-convex smooth functions.
result Adagrad, RMSProp, and AMSGRAD converge to critical points at a similar rate to unbiased case.
Large learning rates lead to various implicit biases in nonconvex optimization.
problem Understanding the conditions under which large learning rates yield edge of stability, balancing, and catapult phenomena.
method Developed a global convergence theory for nonconvex functions without globally Lipschitz continuous gradient, focusing on functions with good regularity.
result These implicit biases are more likely to occur in functions with good regularity, and large learning rates favor flatter regions.
We present a convergence rate analysis for biased stochastic gradient descent (SGD), where individual gradient updates are corrupted by computation errors. We develop stochastic quadratic constraints to formulate a small linear matrix inequality (LMI) whose feasible points lead to convergence bounds of biased SGD. Base…
DML addresses biases in machine learning by estimating nuisance functions.
problem Bias in machine learning models due to nuisance functions.
method Double/Debiased Machine Learning (DML) approach to reduce biases.
result DML allows flexible estimation of nuisance functions without auxiliary assumptions.
The paper addresses learning from biased data samples.
problem Selection bias in training data affects machine learning outcomes.
method Develops a method to create a nearly debiased training population from biased samples.
result The learning rate is nearly as good as in unbiased scenarios.
New method finds unbiased subnetworks in biased models for better OOD performance.
problem How to improve out-of-distribution generalization in deep models.
method Functional modular probing method and Modular Risk Minimization.
result Even in biased models, there are unbiased subnetworks that can achieve better OOD performance.
New method uncovers bias mechanisms in observational studies.
problem Understanding the sources of bias in observational studies.
method Analyzing the relationship between bias magnitude and nuisance function estimators' performance.
result Method can distinguish between common sources of causal bias.
Theoretical analysis of CNNs' inductive biases and their efficiency in approximating functions.
problem Understanding and optimizing the inductive biases in deep CNNs.
method Theoretical analysis combining multichanneling, downsampling, weight sharing, and locality.
result Deep CNNs with O ( log d ) \mathcal{O}(\log d) O ( log d ) depth can approximate any continuous function, and require O ~ ( log 2 d ) \widetilde{\mathcal{O}}(\log^2d) O ( log 2 d ) samples for sparse functions. Integrates inductive biases into VAEs using intermediary latent variables.
problem Ineffective mechanisms for incorporating inductive biases into VAEs.
method InteL-VAEs use an intermediary latent space to control encoding, with a parametric function to enforce desired properties.
result InteL-VAEs lead to better generative models and representations.
Regularized training of an autoencoder typically results in hidden unit biases that take on large negative values. We show that negative biases are a natural result of using a hidden layer whose responsibility is to both represent the input data and act as a selection mechanism that ensures sparsity of the representati…
New method identifies parameters of wider shallow neural networks with biases.
problem Identifying parameters of wide shallow neural networks with biases from finite samples.
method Two-step pipeline: direction of weights via second order information, signs via algebraic evaluations, biases via gradient descent.
result Constructive methods and theoretical guarantees of finite sample identification for wider shallow networks with biases.
This work addresses encoding biases in neural networks by tailoring models with unsupervised losses.
problem Improving neural network representations and reducing the generalization gap.
method Inspired by transductive learning, the authors propose tailoring and meta-tailoring to optimize unsupervised losses during prediction time.
result Models trained with tailoring and meta-tailoring perform better on the task objective after adapting to unsupervised losses.
Paper analyzes biased stochastic approximation with a novel multistep Lyapunov function.
problem Finite-time analysis of biased stochastic approximation algorithms.
method Developed a multistep Lyapunov function to analyze convergence and error bounds.
result First finite-time error bounds for TD- and Q-learning with linear function approximation.
Biased mean regression estimates factors exceeding expected loss or radiation release severity.
problem Estimating factors exceeding expected loss or radiation severity levels.
method Biased mean regression using superexpectation error minimization.
result Equivalent to quantile regression and CVaR optimization under specific conditions.
Survival trees exhibit end-cut preference, leading to biased splits.
problem End-cut preference in survival trees causes biased splits and poor interpretability.
method Proposed a smooth sigmoid surrogate (SSS) approach to replace hard-threshold indicator function.
result Smooth sigmoid surrogate (SSS) effectively mitigates end-cut preference in survival trees.
Periodic activation functions improve neural network reliability and interpretability.
problem Neural networks reinforce hidden biases, making them unreliable and hard to interpret.
method Introduce periodic activation functions in Bayesian neural networks to establish a connection with stationary Gaussian process priors.
result Periodic activation functions, including sinusoidal, triangular, and ReLU, improve model performance and sensitivity to perturbations.
We prove that the binary classifiers of bit strings generated by random wide deep neural networks with ReLU activation function are biased towards simple functions. The simplicity is captured by the following two properties. For any given input bit string, the average Hamming distance of the closest input bit string wi…
New methods for CI testing under model misspecification.
problem Challenges in CI testing with misspecified models.
method Proposes new approximations and upper bounds for testing errors of regression-based CI tests.
result Introduces the Rao-Blackwellized Predictor Test (RBPT) robust against misspecified inductive biases.
We analyze the joint probability distribution on the lengths of the vectors of hidden variables in different layers of a fully connected deep network, when the weights and biases are chosen randomly according to Gaussian distributions, and the input is in { − 1 , 1 } N \{ -1, 1\}^N { − 1 , 1 } N . We show that, if the activation function φ φ φ sat…
Asynchronous stochastic approximations (SAs) are an important class of model-free algorithms, tools and techniques that are popular in multi-agent and distributed control scenarios. To counter Bellman's curse of dimensionality, such algorithms are coupled with function approximations. Although the learning/ control pro…
New approach learns human planning algorithms for reward inference.
problem Learning reward functions from human demonstrations with biases.
method Data-driven approach to learn planning algorithms directly from demonstrations.
result Mixed results: better reward inference but at cost of differentiability.
Self-attention prefers sparse functions of input sequences, reducing sample complexity.
problem Understanding the inductive biases of self-attention in modeling long-range dependencies.
method Theoretical analysis and synthetic experiments to probe sample complexity of learning sparse functions with Transformers.
result Bounded-norm Transformer networks can represent sparse functions of the input sequence with logarithmic sample complexity.
We propose an inference method to estimate sparse interactions and biases according to Boltzmann machine learning. The basis of this method is L 1 L_1 L 1 regularization, which is often used in compressed sensing, a technique for reconstructing sparse input signals from undersampled outputs. L 1 L_1 L 1 regularization impedes the …
Resampling outperforms reweighting for correcting biased data in machine learning models.
problem Correcting sampling bias in machine learning models trained on biased data sets.
method Compared resampling and reweighting techniques, focusing on their performance with stochastic gradient algorithms.
result Resampling outperforms reweighting when combined with stochastic gradient algorithms.
New method for estimating treatment effects without complex propensity models.
problem Estimating treatment effects in dynamic treatment regimes.
method Recursive Riesz representer estimation for de-biasing corrections.
result Directly estimates de-biasing corrections without auxiliary models.
Study on memorization vs. generalization in overparameterized networks.
problem Understanding the trade-off between memorization and generalization in neural networks.
method Examined fully-connected and convolutional networks trained to minimize reconstruction error.
result Different architectures exhibit distinct inductive biases, affecting generalization from a single training example.
Improved speech enhancement with larger neural networks using novel embeddings and biases.
problem Decreased robustness of speech enhancement models to real-world use cases.
method Frequency-positional embeddings, semi-supervised training, biased loss function.
result Better performance on real recordings with improved large neural network architecture.
Bayesian optimization improved for biased data.
problem Adversarial bias in observations, especially hidden confounders.
method Reduction to dueling bandits, information-directed sampling (IDS).
result First efficient kernelized algorithm with regret guarantees.
Paper explores how knowledge distillation transfers inductive biases between models.
problem Transferring inductive biases between models for tasks with limited data.
method Knowledge distillation applied to models with different inductive biases (LSTMs vs. Transformers, CNNs vs. MLPs).
result Effect of inductive biases is transferred through knowledge distillation, impacting both performance and solution characteristics.
Improved text generation with constraints using discrete auto-regressive biasing.
problem Balancing fluency and constraint satisfaction in LLM outputs.
method Discrete Auto-regressive Biasing, leveraging gradients in discrete text space.
result Significantly improved constraint satisfaction with comparable fluency.
This paper introduces hierarchical Gaussian process priors for neural networks to capture weight correlations and inductive biases.
problem Capturing weight correlations and inductive biases in neural networks.
method Hierarchical Gaussian process priors with unit embeddings and input-dependent kernels.
result Hierarchical Gaussian process priors provide competitive predictive performance and desirable uncertainty estimates.
NeuralRBMLE tackles explore-exploit trade-offs in contextual bandits with neural networks.
problem Stochastic contextual bandit problem with general bounded reward functions.
method Reward-biased maximum likelihood estimation with neural networks to enforce exploration.
result Both NeuralRBMLE variants achieve O ~ ( T ) \widetilde{\mathcal{O}}(\sqrt{T}) O ( T ) regret. In this paper, we consider the stochastic iterative counterpart of the value iteration scheme wherein only noisy and possibly biased approximations of the Bellman operator are available. We call this counterpart as the approximate value iteration (AVI) scheme. Neural networks are often used as function approximators, i…
New algorithm finds unbiased subnetworks in biased datasets.
problem Finding unbiased subnetworks in biased neural networks.
method Debiased Contrastive Weight Pruning (DCWP) algorithm.
result DCWP significantly outperforms state-of-the-art debiasing methods.
Algorithm learns fair ranking from biased data.
problem Unfair ranking policies from biased implicit feedback.
method Policy-gradient approach with amortized fairness constraints.
result Efficient algorithm FULTR learns fair policies.
New method discourages models from using bias shortcuts for better generalization.
problem Training models on biased data can lead to poor generalization when bias shifts.
method Train a de-biased representation by encouraging it to differ from biased representations.
result Improved generalization across synthetic and real-world biases.
The paper tackles bandit problems with biased offline data by using causal methods.
problem Improving bandit algorithms with biased offline data that includes confounding and selection biases.
method Formalizes the problem from a causal perspective, categorizes biases, and derives robust bounds for each arm.
result Causal bounds can guide the bandit agent to learn a nearly-optimal decision policy and consistently reduce asymptotic regret.
Machine learning biases in job recommendations can lead to unfair outcomes.
problem Biased recommendations from recommender systems in job matching.
method Addressing biases at various stages of recommender systems training and deployment.
result Techniques can reduce bias in job recommendations, ensuring fair outcomes.
Neural nets learn simple distributions first, then more complex ones.
problem Understanding how neural networks generalize from simple to complex functions.
method Stochastic gradient descent training, synthetic data, CIFAR10, ImageNet pre-training.
result Neural networks initially use lower-order statistics, then higher-order ones.
Gradient-based methods can be biased by distributional asymmetries in bivariate categorical data.
problem Gradient-based causal discovery methods can be biased by distributional asymmetries in bivariate categorical data.
method Identified and examined two distributional biases: Marginal Distribution Asymmetry and Marginal Distribution Shift Asymmetry. Employed two simple models to demonstrate and control these biases.
result Gradient-based methods can be biased by distributional asymmetries, and these biases can be controlled.
Framework assesses autograders' reliability and biases.
problem Mixed reliability and biases in autograders for LLM evaluation.
method Bayesian GLMs to model evaluation outcomes.
result Explicit quantification of scoring differences and biases.
Proposes methods to estimate posterior probability and propensity score functions without assuming constant propensity score.
problem Learning from biased positive-unlabeled data.
method Parametric approach to joint estimation of posterior probability and propensity score functions using maximum likelihood and alternating maximization.
result Proposed methods are comparable or better than existing methods based on Expectation-Maximisation scheme.
Study shows statistical biases can mislead transformer models, impairing their generalization.
problem Statistical biases in transformers affect their ability to generalize.
method Evaluated transformer models on synthetic algorithmic tasks with varying statistical biases.
result Statistical biases lead to overestimation of transformer models' generalization capabilities.