Formulates Markov property for risk-sensitive dynamic optimisation.
problem Risk-sensitive dynamic optimisation problems in discrete time.
method Formulates probabilistic Markov property under dynamic risk framework.
result Property holds for standard risk measures and has multiple equivalent versions.
SenSeI ensures fair models by enforcing invariance on sensitive groups.
problem Ensuring fair machine learning models that respect sensitive groups.
method Designing a transport-based regularizer to enforce invariance on sensitive sets.
result Certifiably fair ML models trained using SenSeI achieve improved fairness metrics.
Torsion sensitive intersection homology was introduced to unify several versions of Poincare duality for stratified spaces into a single theorem. This unified duality theorem holds with ground coefficients in an arbitrary PID and with no local cohomology conditions on the underlying space. In this paper we consider for…
We study a risk sensitive control version of the lifetime ruin probability problem. We consider a sequence of investments problems in Black-Scholes market that includes a risky asset and a riskless asset. We present a differential game that governs the limit behavior. We solve it explicitly and use it in order to find …
We study risk-sensitive imitation learning where the agent's goal is to perform at least as well as the expert in terms of a risk profile. We first formulate our risk-sensitive imitation learning setting. We consider the generative adversarial approach to imitation learning (GAIL) and derive an optimization problem for…
Study examines noise sensitivity of DNNs for binary classification.
problem Understanding non-robustness of DNN classifiers under noise.
method Defined and extended noise sensitivity and stability concepts for Boolean functions, applied to DNN models.
result Sorted out the relation between definitions and properties of DNN architectures under noise.
We analyze how uncertainty in models affects optimization outcomes using Wasserstein distances.
problem Sensitivity of optimization problems to model uncertainty.
method Non-parametric approach using Wasserstein balls to capture uncertainty, providing explicit corrections for value function and optimizer.
result Explicit formulae for first-order corrections to value function and optimizer.
Proposes a method to assess unobserved confounding effects in causal inference.
problem Assessing unobserved confounding in causal inference studies.
method Copula-based normalizing flows with sensitivity parameter ρ. result Estimates average causal effect (ACE) as a function of unobserved confounding strength.
New features generated from kernel methods are minimally dependent on sensitive features.
problem Generating fair features in the presence of sensitive and non-sensitive features.
method Relaxed Maximum Mean Discrepancy criterion, Hilbert-space-valued conditional expectation, plug-in approach.
result Closed-form solution for minimizing dependencies between new and sensitive features.
Classification on imbalanced datasets is a challenging task in real-world applications. Training conventional classification algorithms directly by minimizing classification error in this scenario can compromise model performance for minority class while optimizing performance for majority class. Traditional approaches…
We propose a new class of data-independent locality-sensitive hashing (LSH) algorithms based on the fruit fly olfactory circuit. The fundamental difference of this approach is that, instead of assigning hashes as dense points in a low dimensional space, hashes are assigned in a high dimensional space, which enhances th…
Develops a TL framework for estimating RMST difference in clinical trials.
problem Estimating RMST difference in clinical trials with time-to-event outcomes.
method Targeted learning (TL) framework using pseudo-observations and copy reference (CR) approach for sensitivity analysis.
result Demonstrated the effectiveness of the TL framework using real data.
Improved kernel ridge regression for large datasets using weighted random binning.
problem Efficiently approximating kernel matrices for large-scale datasets.
method Introduced weighted random binning features for locality sensitive hashing.
result Weighted random binning features generate Gaussian processes of any desired smoothness.
Framework for fair predictive models using resampled sensitive attributes.
problem Achieving fair predictions in machine learning models.
method Introducing a discrepancy functional and resampling sensitive attributes.
result Improved performance and equitable uncertainty quantification.
Study finds consumers are more price-sensitive before livestreams than after.
problem Understanding consumer demand during livestreaming lifecycle.
method Examined consumer demand for live events and recorded versions using data from a livestreaming platform.
result Demand is more price-sensitive before livestreams than after.
Iteratively reweighted least squares (IRLS) is a widely-used method in machine learning to estimate the parameters in the generalised linear models. In particular, IRLS for L1 minimisation under the linear model provides a closed-form solution in each step, which is a simple multiplication between the inverse of the we…
We outline a novel clustering scheme for simplicial complexes that produces clusters of simplices in a way that is sensitive to the homology of the complex. The method is inspired by, and can be seen as a higher-dimensional version of, graph spectral clustering. The algorithm involves only sparse eigenproblems, and is …
AOBTM adapts online topic modeling for short app reviews, revealing coherent topics over time.
problem Challenges in inferring latent topics from short, dynamic app reviews over multiple versions.
method Adaptive Online Biterm Topic Model (AOBTM) that addresses sparsity and considers statistical data from previous versions.
result AOBTM finds more coherent topics and outperforms state-of-the-art baselines.
Transforms offline algorithms to online with low regret in random order model.
problem Developing online algorithms with low approximate regret from offline approximation algorithms.
method General reduction theorem and coreset construction method.
result Achieves polylogarithmic ε-approximate regret for various online problems.
Current adoption of machine learning in industrial, societal and economical activities has raised concerns about the fairness, equity and ethics of automated decisions. Predictive models are often developed using biased datasets and thus retain or even exacerbate biases in their decisions and recommendations. Removing …
This paper is an expansion of my lecture for David Epstein's birthday, which traced a logical progression from ideas of Euclid on subdividing polygons to some recent research on invariants of hyperbolic 3-manifolds. This `logical progression' makes a good story but distorts history a bit: the ultimate aims of the chara…
Hamiltonian Monte Carlo (HMC) is a popular Markov chain Monte Carlo (MCMC) algorithm that generates proposals for a Metropolis-Hastings algorithm by simulating the dynamics of a Hamiltonian system. However, HMC is sensitive to large time discretizations and performs poorly if there is a mismatch between the spatial geo…
Proposes a new Lasso method with performance constraints.
problem No control over prediction accuracy for certain individuals.
method Adds quadratic performance constraints to Lasso-based objective functions.
result Defines a constrained sparse regression model through nonlinear optimization.
Improved online learning for fuzzy min-max neural networks.
problem Classification performance issues due to expansion and contraction steps.
method Proposes an improved online learning algorithm without contraction for overlapping hyperboxes.
result Significant improvement in classification accuracy and stability.
Valuing Guaranteed Minimum Withdrawal Benefit (GMWB) has attracted significant attention from both the academic field and real world financial markets. As remarked by Yang and Dai, the Black and Scholes framework seems to be inappropriate for such a long maturity products. Also Chen Vetzal and Forsyth in showed that th…
Stochastic mirror descent (SMD) is a fairly new family of algorithms that has recently found a wide range of applications in optimization, machine learning, and control. It can be considered a generalization of the classical stochastic gradient algorithm (SGD), where instead of updating the weight vector along the nega…
Deep Neural Networks are robust to minor perturbations of the learned network parameters and their minor modifications do not change the overall network response significantly. This allows space for model stealing, where a malevolent attacker can steal an already trained network, modify the weights and claim the new ne…
We reformulate data-dependent constraints to ensure they are always met with high probability.
problem Ensuring fairness and stability in machine learning models with data-dependent constraints.
method Calibrated reformulation of constraints to guarantee satisfaction with a specified probability.
result Our method guarantees that fairness constraints are met at test time with high probability.
Proposes adversarial learning for counterfactual fairness in machine learning.
problem Ensuring fairness at the individual level by simulating counterfactual samples.
method Adversarial neural learning approach to infer counterfactual samples.
result Significant improvements in counterfactual fairness for both discrete and continuous settings.
Improved method for private quantile estimation in datasets with atoms.
problem Private estimation of quantiles in datasets with atoms.
method Application of Inverse Sensitivity mechanism and Heuristically Smoothed JointExp.
result Improved performance on datasets with atoms compared to existing methods.
Improves classifier evaluation by aligning with Total Classification Cost.
problem Lack of consensus on evaluation metrics and class imbalance issues.
method Introduces Weighted Accuracy (WA) and a reweighting framework for cost-sensitive scenarios.
result WA aligns with Total Classification Cost (TCC) minimization under realistic conditions.
HI-SIGMA improves sensitivity in high-dimensional statistical inference with data-driven background models.
problem Performing high-dimensional statistical inference with complex backgrounds in high-energy physics.
method HI-SIGMA uses generative ML models to learn signal and background distributions, incorporating systematic uncertainties.
result HI-SIGMA provides improved sensitivity compared to classifier-based methods.
This paper is concerned with the defense of deep models against adversarial attacks. Inspired by the certificate defense approach, we propose a maximal adversarial distortion (MAD) optimization method for robustifying deep networks. MAD captures the idea of increasing separability of class clusters in the embedding spa…
Prevents sensitive data generation in diffusion models using labeled and unlabeled data.
problem Generating sensitive data in diffusion models using unlabeled data.
method Positive-Unlabeled Diffusion Models, approximating ELBO with labeled and unlabeled data.
result Prevents the generation of sensitive data without compromising image quality.
A framework for sensitivity measures using scoring functions.
problem Constructing sensitivity measures for any elicitable functional.
method Score-based sensitivities constructed via consistent scoring functions.
result Demonstrated intuitive and desirable properties of score-based sensitivities.
This work provides efficient algorithms for approximating ℓ_p sensitivities and related statistics.
problem Estimating the importance of datapoints in high-dimensional datasets.
method Efficient algorithms for computing α-approximation of ℓ_1 sensitivities and total sensitivity using importance sampling and sensitivity computations.
result Real-world datasets have significantly lower intrinsic effective dimensionality than theoretical predictions.
Unified framework for CVA sensitivities, hedging, and risk assessment.
problem Computing and managing Credit Value Adjustment (CVA) sensitivities and risks.
method Probabilistic machine learning and refined regression on simulated data, validated by Monte Carlo methods.
result Identification of optimal sensitivities for practical tasks like hedging and risk assessment.
New methods protect privacy while providing accurate prediction sets.
problem Privacy-preserving conformal prediction for untrusted aggregators.
method Two LDP approaches: k-ary randomized response and binary search response.
result Finite-sample coverage guarantees and robust coverage under randomization.
Principal Component Analysis (PCA) is a popular tool for dimensionality reduction and feature extraction in data analysis. There is a probabilistic version of PCA, known as Probabilistic PCA (PPCA). However, standard PCA and PPCA are not robust, as they are sensitive to outliers. To alleviate this problem, this paper i…
Deep learning interpretation is essential to explain the reasoning behind model predictions. Understanding the robustness of interpretation methods is important especially in sensitive domains such as medical applications since interpretation results are often used in downstream tasks. Although gradient-based saliency …
New method speeds up causal sensitivity analysis.
problem Bounding causal effects in unobserved confounding.
method Amortized approach using prior-data fitted networks.
result Orders of magnitude faster computation.
A new approach to sensitivity analysis without the Sobol decomposition.
problem Traditional sensitivity indices like Sobol indices have limitations.
method Introducing sensitivity measures that generalize existing indices and define interaction effects.
result Sensitivity measures can create new indices and define interaction effects.
Uniform K-homology theory applied to elliptic operators on manifolds with boundary.
problem Developing a theory to study boundary conditions for elliptic operators on non-compact manifolds.
method Theory of relative uniform K-homology, developing a relative index map.
result Uniform K-homology classes of boundary conditions and their connection to the higher ρ-invariant.
New algorithm balances user reward and statistical inference by mixing TS with UR based on difference size.
problem Combining statistical inference with user reward in adaptive experiments.
method TS-PostDiff algorithm that uses UR when differences are small and TS when large.
result TS-PostDiff reduces false positives and increases statistical power for small differences, while maximizing reward for large ones.
Worst-Case Sensitivity measures model sensitivity to uncertainty set size.
problem Model sensitivity to uncertainty set size in Distributionally Robust Optimization.
method Introducing Worst-Case Sensitivity as a measure of model sensitivity, and deriving closed-form expressions for various uncertainty sets.
result DRO solutions can be sensitive to the family and size of the uncertainty set, and worst-case sensitivity reflects these properties.
Simplified equation predicts model sensitivity to data.
problem Understanding model sensitivity to training data is challenging and costly.
method Derived using Bayesian principles, the Memory-Perturbation Equation (MPE) unifies and generalizes existing sensitivity measures.
result Empirical results show sensitivity estimates during training can predict generalization on unseen test data.
Cluster-DP improves differential privacy in randomized experiments by clustering data.
problem Reducing variance in causal effect estimation from differentially private data.
method Cluster-DP leverages a given cluster structure to improve the privacy-variance trade-off.
result Selecting higher-quality clusters decreases the variance penalty without compromising privacy guarantees.
Paper introduces AIF for anomaly detection with variable feature sensitivity.
problem Lack of variable sensitivity in anomaly detection methods.
method Extended Isolation Forest with feature sensitivities (Anisotropic Isolation Forest).
result AIF enables anomaly detection with controllable sensitivity to different features.