New method learns time-varying home field advantage in football.
problem Discovering causal factors behind home field advantage in sports.
method DYNAMO: a novel causal discovery method for non-stationary processes.
result Time-varying home field advantages influenced by referee bias.
FST.ai 2.0 improves Taekwondo decision-making with AI, reducing review time and increasing trust.
problem Fair, transparent, and explainable decision-making in Taekwondo.
method Pose-based action recognition, epistemic uncertainty modeling, interactive dashboards.
result 85% reduction in decision review time, 93% referee trust in AI-assisted decisions.
Protocol assesses better model among two opaque models with minimal interaction.
problem Learning from two provers, one honest, the other potentially deceptive.
method Formulated and implemented a protocol for assessing better models among two opaque models.
result Protocol achieves near-optimal performance with minimal interaction and query access.
This replaces the previous version, by correcting an error in the proof of Theorem 1.4, that was pointed out by the referee.
This is an expanded version of the lecture course the second author gave at Winterbraids VI in Lille in February 2016. Version 2: revision incorporating referee remarks.
Geometrization theorem, fibered case: Every three-manifold that fibers over the circle admits a geometric decomposition. Double limit theorem: for any sequence of quasi-Fuchsian groups whose controlling pair of conformal structures tends toward a pair of projectively measured laminations that bind the surface, there is…
This is an almost self-contained monograph (containing some new results) on left-orderable groups which mostly rely on dynamical and probabilistic aspects, but also on geometric, combinatorial, analytic, and topological ones. This new version contains many improvements, corrections and updates, many of them suggested b…
This manuscript contains a detailed proof of the Poincare Conjecture. The arguments we present here are expanded versions of the ones given by Perelman in his three preprints posted in 2002 and 2003. This is a revised version taking in account the comments of the referees and others. It has been reformatted in the AMS …
Improve exposition and explain metric bundle equivalence.
problem Improving exposition and explaining metric bundle equivalence.
method Improved exposition and appendix explaining equivalence of flaring conditions.
result Equivalence of flaring conditions explained.
Given a map f: M \to M of closed topological manifolds we define torsion obstructions whose vanishing is a necessary condition for f being homotopy equivalent to a projection of a locally trivial fiber bundle. If N = S^1, these torsion obstructions are identified with the ones due to Farrell. We have changed the exposi…
This is an investigation of the role of shuffling and concatenating in the theory of graph drawing. A simple syntactic description of these and related operations is proved complete in the context of finite partial orders, as general as possible. An explanation based on that is given for a previously investigated colla…
Study evaluates two-sample tests for validating generative models in high dimensions.
problem Validating the performance and efficiency of non-parametric two-sample tests for high-dimensional generative models.
method Proposes and evaluates the sliced Wasserstein distance, mean of Kolmogorov-Smirnov statistics, and novel sliced Kolmogorov-Smirnov statistic.
result One-dimensional-based tests provide comparable sensitivity to other multivariate metrics but with lower computational cost.
A referee found an error in the proof of the Theorem 2 that we could not fix. More precisely, the proof of Lemma 2.1 is incorrect. Hence the fact that integer cohomology of complement of toric Weyl arrangements is torsion free is still a conjecture. ----- A toric arrangement is a finite set of hypersurfaces in a comple…
In this paper we give detailed construction of G-equivariant Kuranishi chart of moduli spaces of pseudo-holomorphic curves to a symplectic manifold with G-action, for an arbitrary compact Lie group G. The proof is based on the deformation theory of {\it unstable} marked curves using the language of Lie groupoid (…
Complex b-6j symbols relate to hyperbolic tetrahedron volumes and determinants.
problem Analyzing asymptotics of complex b-6j symbols. method Relating asymptotics to hyperbolic tetrahedron volumes and determinants.
result Complex b-6j symbols' asymptotics linked to tetrahedron volumes and determinants. Working in high-dimensional latent spaces, the internal encoding of data in Variational Autoencoders becomes naturally sparse. We discuss this known but controversial phenomenon sometimes refereed to as overpruning, to emphasize the under-use of the model capacity. In fact, it is an important form of self-regularizatio…
The paper quantifies aleatoric and epistemic uncertainties with random forests.
problem Addressing uncertainty in machine learning predictions.
method Using decision trees and random forests to measure aleatoric and epistemic uncertainties.
result Random forests effectively quantify uncertainties compared to deep neural networks.
We study the discriminant of a degree 4 extension given by a deformed bidouble cover, i.e., by equations z^2= u + a w, w^2= v + bz. We first show that the discriminant surface is a quartic which is cuspidal on a twisted cubic, i.e.,is the discriminant of the general equation of degree 3. We then take a(u,v), b(u,v) and…
(NOTE: per referee comments, this article has been split; it is now superseded by "Existence of thread-wire minimizers" and "Near-wire thread-wire minimizers"; please see http://www.bkstephens.net.) Alt's thread problem asks for least-area surfaces bounding a fixed "wire" curve and a movable "thread" curve of length L.…
Sparse coding (Sc) has been studied very well as a powerful data representation method. It attempts to represent the feature vector of a data sample by reconstructing it as the sparse linear combination of some basic elements, and a L2 norm distance function is usually used as the loss function for the reconstructio…
Research shows bias in machine learning can be due to algorithmic flaws, not just data.
problem Underestimation bias in machine learning algorithms.
method Initial research to understand factors contributing to bias in classification algorithms.
result Regularization methods to address overfitting can also accentuate bias.
The paper develops stability criteria for real reductive Lie groups acting on manifolds.
problem Analyzing stability of real reductive Lie group actions on manifolds.
method Introduced a gradient map and maximal weight function to characterize stability conditions.
result Characterized stability, semistability, and polystability using numerical criteria.
The first two authors showed in~\cite{AM1} how the Conley-Zehnder index of any contractible periodic Reeb orbit of a non-degenerate toric contact form on a good toric contact manifold with zero first Chern class, i.e. a Gorenstein toric contact manifold, can be explicitly computed using moment map data. In this paper w…
Deep hedging uses RL to minimize risk in financial markets.
problem Minimizing risk in financial markets using reinforcement learning.
method Trains a neural network policy via Monte Carlo simulation and stochastic gradient descent.
result Deep hedging algorithm falls within the RL category.
Financial LLMs need explicit bias consideration to avoid invalid results.
problem Finance-specific biases inflate performance and contaminate backtests.
method Identified five recurring biases and proposed a Structural Validity Framework.
result Explicit bias consideration is necessary for valid deployment claims.
We study the phenomenon of bias amplification in classifiers, wherein a machine learning model learns to predict classes with a greater disparity than the underlying ground truth. We demonstrate that bias amplification can arise via an inductive bias in gradient descent methods that results in the overestimation of the…
It has been noticed that some external CVIs exhibit a preferential bias towards a larger or smaller number of clusters which is monotonic (directly or inversely) in the number of clusters in candidate partitions. This type of bias is caused by the functional form of the CVI model. For example, the popular Rand index (R…
Mitigates gender bias amplification in model predictions.
problem Gender bias amplification in model predictions.
method Posterior regularization to mitigate bias.
result Almost removes gender bias amplification in model predictions.
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.
We quantify causal bias in continuous treatment settings.
problem Identifying and quantifying causal bias in continuous treatment scenarios.
method Developed a novel characterization of causal bias in structural causal models, proving conditions for zero bias and efficient estimation.
result Causal bias can be estimated efficiently under certain structural equation restrictions, allowing for causal regularization of predictive models.
The paper introduces Relative Bias to quantify LLM bias systematically.
problem Quantifying bias in LLMs is challenging due to ambiguity and rapid model emergence.
method Relative Bias framework using Embedding Transformation and LLM-as-a-Judge methodologies.
result The two scoring methods show strong alignment, providing a systematic approach.
Interpolated-MLPs control inductive bias for better performance in low-compute tasks.
problem Low-compute performance gap between MLPs and CNNs.
method Introduced Interpolated MLP (I-MLP) approach to control inductive bias incrementally.
result Continuous logarithmic relationship between inductive bias and performance in low-compute tasks.
SSMs have a built-in bias towards low-frequency components, which can be adjusted.
problem Frequency bias in SSMs affects their performance on long-range sequences.
method Proposed two mechanisms to tune frequency bias: scaling initialization or applying a Sobolev-norm-based filter.
result Tuning frequency bias improves SSMs' performance on long-range sequence learning tasks.
A bias classifier is introduced to resist adversarial attacks.
problem Resisting adversarial attacks on deep neural networks (DNNs).
method Introducing the bias part of a DNN with Relu as the activation function as a classifier, and adding a random first-degree part to make it information-theoretically safe.
result The bias classifier is more robust than DNNs of similar size against adversarial attacks.
UBM transfers bias mitigation from upstream to downstream tasks efficiently.
problem Bias in fine-tuned language models across various tasks.
method Apply bias mitigation to an upstream model, then fine-tune a downstream model on this mitigated model.
result UBM effects transfer to new downstream tasks, creating less biased models.
Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for different contexts, to developing algorithms to mitigate bias. In natural language processing, gender bias has been shown to exist in contex…
Active learning introduces bias; this paper fixes it.
problem Bias in active learning due to non-representative training data.
method Formalized bias, identified situations where it's harmful/helpful, introduced corrective weights.
result Corrective weights can improve active learning, especially with overparameterized models.
Bias correction improves language model training performance.
problem Stochastic update bias in preconditioned optimizers.
method Cross-fitted preconditioning and variance-corrected inversion.
result Reduces held-out pretraining loss by 0.15 nats.
Ensembles improve classifier performance by reducing bias, not variance.
problem Improving classifier performance through ensemble methods.
method Extended bias-variance decomposition for classification tasks, introducing dual reparameterization.
result Ensembling reduces bias in classifiers, contrary to the traditional view.
Study finds gender bias in human evaluators and shows how machine learning can mitigate it.
problem Gender bias in human decision-making on micro-lending platforms.
method Structural econometric model and machine learning algorithms trained on real-world data.
result Machine learning algorithms can mitigate both preference-based and belief-based biases.
Reduces gender bias in patient notes while maintaining medical classification accuracy.
problem Bias in natural language processing of patient notes.
method Identifying and removing gendered language using BERT-based classifiers, then augmenting data to maintain performance.
result Minimal degradation in health condition classification tasks with data augmentation.
Develops a method to quantify racial bias in law enforcement systems.
problem Quantify racial bias in law enforcement systems considering criminality and multi-stage interactions.
method Multi-stage causal framework incorporating criminality.
result Identifies three canonical scenarios of racial bias in law enforcement.
Study analyzes bias interactions in multimodal models using simulation-based methods.
problem Analyzing dynamic bias interactions in multimodal models to ensure fairness and equity.
method Simulation-based heuristic approach to compute bias scores for text-only, image-only, and multimodal embeddings.
result Multimodal bias interactions can be amplification, mitigation, or neutral, with text bias often dominant.
Study uncovers bias in image classification models using attribution maps.
problem Data bias in image classification models.
method Created an artificial dataset with known bias, trained CNNs, and used attribution maps to inspect decisions.
result Different attribution map techniques highlight bias better than others, and metrics support bias identification.
Study on bias and extrapolation in LSA with Markovian data, showing bias reduction with Richardson-Romberg extrapolation.
problem Bias in LSA with constant stepsizes and Markovian data.
method Viewing LSA as a Markov chain, proving convergence and bias expansion, and applying Richardson-Romberg extrapolation.
result Bias is proportional to the stepsize up to higher order terms, and Richardson-Romberg extrapolation reduces the bias.
The paper detects and identifies bias in data using a counterfactual approach.
problem Detecting and identifying bias in data, especially in medical image classification.
method A global explanation framework using the counterfactual approach to identify bias causing artifacts.
result Black frames significantly influence Convolutional Neural Network's prediction, changing benign to malignant.
Federated learning can propagate bias from a few parties to all participants.
problem Bias from a few parties in federated learning can spread to all participants.
method Analysis of naturally partitioned real-world datasets.
result Bias in federated learning is higher than in centralized training.
Study shows how bias in optimization affects robustness in adversarial settings.
problem Understanding and mitigating implicit bias in adversarially robust models.
method Analyzes the implicit bias in robust empirical risk minimization and its impact on generalization.
result Implicit bias in optimization can significantly affect robust generalization.