Improves model robustness to shifts in subpopulations.
problem Poor performance of ML models under data distribution shifts.
method Develops group-aware priors (GAP) over neural network parameters.
result Training with GAP yields state-of-the-art performance.
We describe a pair of invariants for actions of finite groups on shifts of finite type, the left-reduced and right-reduced shifts. The left-reduced shift was first constructed by U. Fiebig, who showed that its zeta function is an invariant, and in fact equal to the zeta function of the quotient dynamical system. We als…
Undersampling often outperforms other methods in nonparametric classification.
problem Distribution shift challenges in nonparametric binary classification.
method Proved undersampling is minimax optimal in worst-case scenarios.
result Undersampling is a robustness intervention with theoretical guarantees.
Introduces derived Lie n-groupoids with shifted symplectic structures.
problem Defines structures for higher groupoids and their symplectic properties.
method Introduced derived Lie n-groupoids and their shifted symplectic structures, defining shifted lagrangian structures and proving composition well-defined.
result Shows that the framework includes various reduction procedures.
Big mapping class groups of infinite type surfaces have infinite asymptotic dimension.
problem Understanding asymptotic dimension of big mapping class groups of infinite type surfaces.
method Analyzing big mapping class groups with coarsely bounded generating sets and essential shifts.
result Big mapping class groups of infinite type surfaces have infinite asymptotic dimension.
Improves overparameterized models' robustness to distribution shifts.
problem Accuracy drop on testing distributions different from training.
method Importance tempering to improve decision boundaries.
result State-of-the-art results on worst group classification tasks.
Improves model calibration and selection in unsupervised domain adaptation.
problem Distribution shifts in unsupervised domain adaptation.
method Developed a novel importance weighted group accuracy estimator.
result Improves state-of-the-art performances by 22% in model calibration and 14% in model selection.
Unified framework for fairness, robustness, and distribution shifts.
problem Diverse failure modes of machine learning systems.
method Formalizes biases as violations of conditional independence and proves equivalence conditions.
result Equivalent effects of biases in different failure modes under specific conditions.
Improves model fairness under changing bias between labels and sensitive groups.
problem Fairness of models deteriorates when bias between labels and sensitive groups changes.
method Introduces correlation shifts to explicitly capture bias changes and proposes a pre-processing step to adjust data ratios.
result Our approach effectively improves model accuracy and fairness, both synthetic and real datasets.
New algorithm provides robust uncertainty quantification without parameter tuning.
problem Real-world machine learning predictors need reliable uncertainty quantification.
method Parameter-free, group-conditional online prediction algorithm.
result Achieves best group-conditional coverage guarantees.
Paper tackles target shift in zero-shot learning using adversarial learning.
problem Target shift in zero-shot learning leads to performance degradation.
method Estimates target shift using class-attribute mapping and applies grouped adversarial learning.
result Improves zero-shot learning performance on multiple datasets.
Paper shows fairness and domain adaptation can work together.
problem Algorithmic bias and distributional shifts in ML models.
method Leveraging fairness and distribution shifts, the paper shows how domain adaptation methods can mitigate bias.
result Enforcing individual fairness can improve out-of-distribution accuracy under covariate shift.
Study examines Indian equity mutual funds' investment style and risk-shifting.
problem Understanding how Indian equity mutual funds' investment styles affect their returns.
method Estimating size and style beta coefficients, identifying breakpoints, analyzing investment styles, and assessing risk-shifting intensity.
result Funds can enhance returns by shifting to high-return styles like Small Value and Small Blend.
New shifting chain map enhances quandle invariants for links.
problem Enhancing quandle invariants for links and surfaces.
method Introducing a shifting chain map σ and its pull-back σ# to transform cocycles.
result Shifting chain map σ# transforms 2-cocycles to 3-cocycles, enhancing invariants.
Quantization of (-1)-shifted derived Poisson manifolds via BV-infinity operators.
problem Quantizing (−1)-shifted derived Poisson manifolds. method Using BV-infinity operators on the space of Berezinian half-densities, proving quantization via lifting of Maurer-Cartan elements.
result Quantization of (−1)-shifted derived Poisson manifolds is equivalent to the vanishing of the second Poisson cohomology group. We investigate in detail the connection between harmonic maps from Riemann surfaces into the unitary group $\U(n)$ and their Grassmannian models: these are families of shift-invariant subspaces of $L^2(S^1,\C^n)$. With the help of operator-theoretic methods we derive a criterion for finiteness of the uniton number whic…
Paper tackles unsupervised learning under latent label shift across domains.
problem Discovering classes from unlabeled data with shifting label distributions.
method Introduces unsupervised learning under Latent Label Shift (LLS), leveraging domain-discriminative models.
result Proves that with domain information, unsupervised classification can improve upon standard methods.
Multi-task learning leverages shared information among data sets to improve the learning performance of individual tasks. The paper applies this framework for data where each task is a phase-shifted periodic time series. In particular, we develop a novel Bayesian nonparametric model capturing a mixture of Gaussian proc…
Study shows how to count and equidistribute cusped Hitchin representations with entropy gaps.
problem Counting and equidistribution of cusped Hitchin representations.
method Renewal theorem of Kesseböhmer and Kombrink applied to count and equidistribute.
result Entropy gaps at infinity allow for counting and equidistribution results.
New methods adapt conformal prediction to unknown subpopulation shifts.
problem Failure of conformal prediction under unknown subpopulation shifts.
method Proposes new methods that adapt conformal prediction to unknown subpopulation shifts without explicit subpopulation labels.
result Ensures valid coverage guarantees without explicit knowledge of subpopulation structure.
The study examines if enforcing fairness helps mitigate bias due to demographic shifts.
problem Bias in ML models due to underrepresented subpopulations in training data.
method Theoretical and simulation analysis of fairness enforcement in target domains.
result Enforcing fairness can lead to the Bayes model in the target domain under certain conditions.
New method prevents classifiers from relying on spurious correlations.
problem Group invariant learning fails to prevent classifiers from depending on spurious correlations.
method Statistical independence tests to construct groups and reweight samples by group label proportion.
result New method significantly outperforms existing group invariant learning methods in generalizing to spurious correlation shifts.
ROME improves algorithmic fairness by learning latent group structure robustly.
problem Latent subgroup disparities and distribution shifts in machine learning models.
method ROME uses an Expectation-Maximization algorithm for linear models and a neural Mixture-of-Experts for nonlinear settings.
result ROME significantly improves fairness compared to standard methods while maintaining average performance.
New method estimates grouping loss in neural networks to improve confidence scores.
problem Improving confidence scores in neural networks to reflect true posterior probabilities.
method Proposed an estimator to approximate the grouping loss.
result Modern neural networks exhibit grouping loss, especially in distribution shifts.
A Lie group has a unique metric when viewed as a flat absolute parallelism.
problem Understanding different metrics on Lie groups and their curvature properties.
method Shifted perspective of viewing Lie groups as flat absolute parallelisms.
result Lie groups have a canonical metric when viewed in this new way.
Following the financial crisis of the late 2000s, policy makers have shown considerable interest in monitoring financial stability. Several central banks now publish indices of financial stress, which are essentially based upon market related data. In this paper, we examine the potential for improving the indices by de…
New equivariant filters improve graph classification.
problem Designing deep learning models for graph symmetries.
method Nonlinear spectral filters (NLSFs) that are equivariant to graph functional shifts.
result NLSFs outperform existing spectral GNNs in graph classification.
New subgroups of mapping class groups constructed for infinite-type surfaces.
problem Constructing new subgroups of mapping class groups for infinite-type surfaces.
method Utilization of special homeomorphisms called shift maps and multipush maps.
result Countably (and uncountably in certain cases) many non-conjugate embeddings of subgroups into mapping class groups.
Study shows cross-domain X-ray prediction performance discrepancies and label shifts.
problem Quantifying generalization limits across different X-ray datasets.
method Large-scale study on multiple X-ray datasets, focusing on performance and label shifts.
result Interesting discrepancies found between model performance and agreement, and concept similarity across tasks.
This note outlines a method for clustering time series based on a statistical model in which volatility shifts at unobserved change-points. The model accommodates some classical stylized features of returns and its relation to GARCH is discussed. Clustering is performed using a probability metric evaluated between post…
Audited Conformal Prediction improves conditional coverage in pretrained models under distribution shift.
problem Uncertainty quantification for pretrained models under unknown distribution shift
method Leverages a small labeled dataset to train an audit model for marginal coverage, integrates outputs into conformal prediction framework
result Significantly higher conditional coverage than existing approaches
For any knot, the following are equivalent. (1) The infinite cyclic cover has uncountably many finite covers; (2) there exists a finite-image representation of the knot group for which the twisted Alexander polynomial vanishes; (3) the knot group admits a finite-image representation such that the image of the fundament…
The paper integrates quasi-Poisson manifolds into multiplicative D-valued moment maps.
problem Integrating quasi-Poisson manifolds into a broader geometric framework.
method Develops new aspects of shifted symplectic and Poisson geometry, establishing Lie-type correspondences and systematic constructions.
result Identifies multiplicative D-valued moment maps integrating quasi-Poisson manifolds, extending known constructions.
Improved neural networks by combining group DRO with regularization.
problem Overparameterized neural networks can fail on atypical groups due to spurious correlations.
method Coupling distributionally robust optimization (DRO) with increased regularization.
result Significant improvements in worst-case group accuracy, maintaining high average accuracy.
New framework learns sufficient invariant features robustly across distribution shifts.
problem Learning robust models under distribution shifts between training and test datasets.
method Sufficient Invariant Learning (SIL) framework and Adaptive Sharpness-aware Group Distributionally Robust Optimization (ASGDRO) algorithm.
result Empirical evaluations confirm ASGDRO's robustness against distribution shifts.
New method GSAT improves robustness against structured perturbations.
problem Structured perturbations in biological data.
method Formulates GSAT as a non-convex concave minimax optimization problem and solves it with GDADMM.
result Improves robustness against group-sparse and rank-constrained perturbations.
Homomorphisms on quandle cohomology groups that raise the dimensions by one are studied in relation to the cocycle state-sum invariants of knots and knotted surfaces. Skein relations are also studied.
CCI combines Bayesian and gradient boosting to create fair, reliable credit risk scores.
problem Tackles high-stakes lending decisions with changing data distributions and fairness constraints.
method Combines Bayesian neural risk scorer and fairness-constrained gradient boosting with shift-aware fusion.
result CCI achieves best trade-off between discrimination, calibration, stability, and fairness.
We prove a version of the affine Kempf-Ness theorem for non-algebraic symplectic structures and shifted moment maps, and use it to describe hyperkahler quotients of T*G, where G is a complex reductive group.
New approach for fair predictions under changing data distributions.
problem Fairness in classification algorithms under covariate shift.
method Proposes a robust predictor that satisfies fairness and maintains statistical properties of source data.
result Demonstrates improved fairness and target performance on benchmark tasks.
Isomorphic algebra connects Toeplitz to Heisenberg group.
problem Connecting Toeplitz algebra to Heisenberg group.
method Isomorphism between Toeplitz algebra and Heisenberg group ideal.
result Found isomorphism between algebra and Heisenberg group ideal.
Study highlights robustness issues in healthcare diagnostic models due to distribution shifts.
problem Robustness of diagnostic models in healthcare is compromised by distribution shifts.
method Theoretical analysis and simulation studies to understand and mitigate shortcuts learned by models.
result Ignoring covariates or using invariant learning approaches leads to non-robust predictors.
Given a TQFT in dimension d+1, and an infinite cyclic covering of a closed (d+1)-dimensional manifold M, we define an invariant taking values in a strong shift equivalence class of matrices. The notion of strong shift equivalence originated in R. Williams' work in symbolic dynamics. The Turaev-Viro module associated to…
In this paper, by modifying the argument shift method,we prove Liouville integrability of geodesic flows of normal metrics (invariant Einstein metrics) on the Ledger-Obata n-symmetric spaces $K^n/\diag(K)$, where K is a semisimple (respectively, simple) compact Lie group.
In this paper, we formulate a new local move on virtual knot diagram, called arc shift move. Further, we extend it to another local move called region arc shift defined on a region of a virtual knot diagram. We establish that these arc shift and region arc shift moves are unknotting operations by showing that any virtu…
TTLSA adapts models to label shifts across domains with nuisance factors.
problem Adapting models to changes in label distributions with nuisance factors.
method TTLSA uses EM on unlabeled samples to adapt a trained model to new label distributions.
result TTLSA improves model performance over invariance methods and baseline methods.
Twisted Alexander invariants have been defined for any knot and linear representation of its group. The invariants are generalized for any periodic representation of the commutator subgroup of the knot group. Properties of the new twisted invariants are given. Under suitable hypotheses, reciprocality and bounds on the …
Study on unknotting twisted knots using arc shift and region arc shift moves.
problem Unknotting twisted knots and finding bounds for region arc shift number.
method Introduced arc shift move and region arc shift move for twisted knots.
result Found families of twisted knots with specific arc shift and region arc shift numbers.