The study examines how bias affects hypothesis formation in neural networks.
problem Characterizing the impact of bias on hypothesis formation in neural networks.
method An automated data-driven projection pursuit neural network to extract and select features for binary classification.
result The refinement of a working hypothesis converges to a robust multivariate perception of data.
New method quantifies inductive bias for machine learning tasks.
problem Quantifying the amount of inductive bias in machine learning models.
method Estimates inductive bias by modeling loss distribution of random hypotheses.
result Higher dimensional tasks require greater inductive bias.
This thesis argues for learning representations from multiple similar tasks for better generalization.
problem Insufficient information in a single task for good generalization.
method Introduces the concept of an environment of a learner and uses a sample from it to learn a representation.
result Learning a representation from n tasks reduces the number of examples required for each task by a factor of n. Interview study reveals considerations for designing semi-automated bias detection tools.
problem Detecting and mitigating machine learning biases.
method Interview study with 11 machine learning practitioners.
result Four considerations identified for tool design.
Automates selection and visualization of model responses in various directions.
problem Manual selection and limited visualization of PDPs.
method Formalizes method for automating PDP selection and extends to arbitrary directions.
result Demonstrates usefulness across model selection, bias detection, and latent space exploration.
Automates bias control in reinforcement learning algorithms.
problem Overestimation bias in reinforcement learning algorithms.
method Data-driven approach for automatic selection of bias control hyperparameters.
result Significant reduction in the number of interactions while maintaining performance.
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.
Machine learning (ML) is increasingly deployed in real world contexts, supplying actionable insights and forming the basis of automated decision-making systems. While issues resulting from biases pre-existing in training data have been at the center of the fairness debate, these systems are also affected by technical a…
A RL framework selects features to balance bias and accuracy dynamically.
problem Bias in automated feature selection when predictors are correlated.
method Multi-component reward function with policy gradient for dynamic regularization and bias mitigation.
result Model balances fairness and accuracy during training.
Estimates peeking effects in p-values to correct bias.
problem Data peeking biases reported p-values downward.
method Develops mechanisms to estimate running extrema of test statistics.
result Corrects bias in p-values due to peeking.
The paper refutes the manifold hypothesis for image data and proposes the union of manifolds hypothesis.
problem The manifold hypothesis fails to capture the structure of image data.
method Empirical verification of the union of manifolds hypothesis on image datasets.
result Image data lies on a disconnected set with varying intrinsic dimensions.
FairVIC improves fairness in neural networks without sacrificing accuracy.
problem Mitigating bias in automated decision-making systems, particularly in deep learning models.
method Integrates variance, invariance, and covariance terms into the loss function during training to abstract fairness concepts.
result Significant improvements in fairness across all tested metrics without compromising accuracy.
Paper addresses bias in search intent affecting click behavior.
problem Bias in user search intent affects click behavior and relevance.
method Proposes a search intent bias hypothesis to improve click models.
result Click models can better interpret user clicks and improve retrieval performance.
Research develops a generic method for evaluating trading platform components.
problem Machine learning in finance is bespoke, opaque, and lacks reproducibility.
method Generic methodology based on hypothesis testing.
result Selected trading pattern is partially supported by statistics.
Paper outlines a new mathematical language for experiments.
problem Formalizing the scientific process for automation.
method Formulates the scientific process in precise mathematical language.
result Novel contributions in data processing, bias variance, and deficiency.
Study evaluates gender bias in relation extraction systems.
problem Gender bias in relation extraction systems.
method Created WikiGenderBias dataset, evaluated systems for bias, analyzed bias mitigation techniques.
result NRE systems exhibit gender bias in predictions.
New method reduces bias in NLI models using ensemble adversarial training.
problem Spurious correlations between hypotheses and entailment classes in NLI datasets.
method Adversarial training with an ensemble of classifiers to reduce bias in sentence representations.
result Ensemble adversarial training produces more robust NLI models, outperforming previous methods.
Data that is gathered adaptively --- via bandit algorithms, for example --- exhibits bias. This is true both when gathering simple numeric valued data --- the empirical means kept track of by stochastic bandit algorithms are biased downwards --- and when gathering more complicated data --- running hypothesis tests on c…
Develops tools to audit ML models for bias and unfairness.
problem Auditing ML models for individual bias and unfairness.
method Formalizes the task as an optimization problem and develops inferential tools for the optimal value.
result Demonstrates the utility of tools in revealing biases in COMPAS recidivism prediction instrument.
EFI automates statistical inference for big data.
problem Statistical inference for model parameters based on observations.
method EFI uses stochastic gradient Markov chain Monte Carlo and sparse deep neural networks.
result EFI provides higher fidelity in parameter estimation and automates the inference process.
Statistical hypothesis testing serves as statistical evidence for scientific innovation. However, if the reported results are intentionally biased, hypothesis testing no longer controls the rate of false discovery. In particular, we study such selection bias in machine learning models where the reporter is motivated to…
Study improves robust nonparametric regression in heavy-tailed noise.
problem Robust nonparametric regression with heavy-tailed noise and unbounded functions.
method Huber regression in reproducing kernel Hilbert spaces (RKHS), probabilistic effective hypothesis space, new comparison theorems.
result Explicit finite-sample error bounds and convergence rates for Huber regression in RKHS under heavy-tailed noise.
SGD noise has no bias advantage in online learning, contrary to offline learning.
problem The role of SGD noise in online learning.
method Extensive empirical analysis of image and language data.
result Small batch sizes do not confer any implicit bias advantages in online learning.
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.
Fake engagement is one of the significant problems in Online Social Networks (OSNs) which is used to increase the popularity of an account in an inorganic manner. The detection of fake engagement is crucial because it leads to loss of money for businesses, wrong audience targeting in advertising, wrong product predicti…
This paper explores how enforcing equivariance constraints limits neural network expressivity and proposes compensatory model size increases.
problem The impact of enforcing equivariance constraints on the expressive power of neural networks.
method Examined 2-layer ReLU networks, analyzed boundary hyperplanes and channel vectors, and constructed upper bounds on model size required for compensation.
result Enforcing equivariance constraints reduces the expressive power of neural networks, but this can be compensated by increasing model size.
New method uses LLMs to generate detailed scientific hypotheses.
problem Generating detailed, actionable scientific hypotheses from coarse initial directions.
method Hierarchical search method that incrementally adds details to hypotheses.
result Hierarchical search method consistently outperforms strong baselines on expert-annotated hypotheses.
Build accurate DNN models requires training on large labeled, context specific datasets, especially those matching the target scenario. We believe advances in wireless localization, working in unison with cameras, can produce automated annotation of targets on images and videos captured in the wild. Using pedestrian an…
Deciding effective and timely preventive measures against complex social problems affecting relatively low income geographies is a difficult challenge. There is a strong need to adopt intelligent automation based solutions with low cost imprints to tackle these problems at larger scales. Starting with the hypothesis th…
We present a general framework for hypothesis testing on distributions of sets of individual examples. Sets may represent many common data sources such as groups of observations in time series, collections of words in text or a batch of images of a given phenomenon. This observation pattern, however, differs from the c…
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.
Training dynamics reveal neural network complexity.
problem Understanding the complexity of neural networks during training.
method Relating the Lipschitz constant and training behavior of neural networks.
result Steady training and bounded complexity in far regions of input space.
Vector embedding is a foundational building block of many deep learning models, especially in natural language processing. In this paper, we present a theoretical framework for understanding the effect of dimensionality on vector embeddings. We observe that the distributional hypothesis, a governing principle of statis…
Annotating automotive radar data is a difficult task. This article presents an automated way of acquiring data labels which uses a highly accurate and portable global navigation satellite system (GNSS). The proposed system is discussed besides a revision of other label acquisitions techniques and a problem description …
Automates feature extraction from JSON data for machine learning.
problem Manual feature engineering for JSON data is laborious, lossy, and prone to bias.
method Automates feature extraction using Mill.jl and JsonGrinder.jl.
result Creates a differentiable machine learning model from raw JSON samples.
The power of machine learning systems not only promises great technical progress, but risks societal harm. As a recent example, researchers have shown that popular word embedding algorithms exhibit stereotypical biases, such as gender bias. The widespread use of these algorithms in machine learning systems, from automa…
Characterizes inductive bias in multi-channel linear CNNs with bounded weight norm.
problem Understanding the inductive bias in multi-channel linear convolutional networks.
method Function space characterization and empirical testing of gradient descent.
result The inductive bias depends on the number of output channels for multi-channel inputs but not for single-channel inputs.
The paper automates policy learning for nonlinear welfare criteria using machine learning and debiasing techniques.
problem Learning optimal policies from observational data with nonlinear welfare criteria.
method Modeling a nonlinear welfare criterion with a utility function, estimating propensity scores with machine learning, and using sieve approximations and cross-validation for model selection.
result The proposed policy learning method satisfies oracle inequalities, providing theoretical guarantees on performance.
Algorithm corrects bias in classification data.
problem Underrepresentation and intersectional bias in classification data.
method Estimate group-wise drop-out rates with small unbiased data, construct reweighting scheme, and present algorithm.
result Efficiently approximate loss of any hypothesis on true distribution.
New method improves feature importance assessment in random forests.
problem Improving feature importance measures for random forests.
method Hypothesis testing via self-normalized feature-residual correlation test (FACT).
result The method provides theoretically justified feature importance tests with controlled type I error and appealing power.
New active learning method uses combinatorial coverage to improve data transfer and reduce bias.
problem Inability to transfer sampled data to new models and sampling bias issues.
method Data-centric active learning methods utilizing combinatorial coverage.
result Sampling data with coverage leads to better data transfer and competitive sampling bias.
COMET learns monotonic neural networks by incorporating counterexamples.
problem Enforcing monotonicity constraints in neural networks for real-world tasks.
method Counterexample-guided learning technique for ReLU neural networks.
result COMET achieves state-of-the-art results and improves model quality.
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.
New method improves regression estimates, reducing bias.
problem Omitted variable bias in high-dimensional linear regression.
method Post-Double-Autometrics, an alternative to Post-Double-Lasso.
result Post-Double-Autometrics outperforms Post-Double-Lasso.
A2A metric evaluates bias correction methods, reducing ATE estimation errors.
problem Selection biases in non-randomized studies of medical treatments.
method Propensity score matching (PSM) with novel metric A2A.
result Reduces ATE estimation errors by up to 90% across synthetic and real-world datasets.
With recent advances in high throughput technology, researchers often find themselves running a large number of hypothesis tests (thousands+) and esti- mating a large number of effect-sizes. Generally there is particular interest in those effects estimated to be most extreme. Unfortunately naive estimates of these effe…
A new estimator corrects bias in high-dimensional predictive regressions.
problem Bias in high-dimensional predictive regressions.
method IVX-desparsified LASSO (XDlasso) estimator.
result Corrects both shrinkage and Stambaugh bias.
A new method debiases multiple target parameters without IFs.
problem Debiasing multiple target parameters in nonparametric models.
method Kernel Debiased Plug-in Estimation (KDPE) using TMLE and reproducing kernel Hilbert spaces.
result KDPE simultaneously debiases all pathwise differentiable target parameters.