The paper explores how adversarial risk is obscured by current evaluation methods.
problem The dangers of evaluating adversarial robustness against weak attacks.
method Formalizing 'adversarial risk' and 'obscurity to an adversary,' developing tools to identify obscured models.
result Gradient-free optimization techniques can decrease the accuracy of adversarial defenses to near zero.
BriarPatches obscure sensitive attributes to achieve demographic parity.
problem Achieving demographic parity in model predictions.
method Pixel-space interventions that obscure sensitive attributes from classifier representations.
result BriarPatches push downstream predictors towards demographic parity.
New measures quantify uncertainty in survival models for maintenance tasks.
problem Uncertainty in survival models for maintenance tasks.
method Formal measures of ambiguity, discrepancy, and obscurity introduced.
result Multiple accurate survival models may yield conflicting risk estimates.
This paper finds universal perturbations to fool black-box ML classifiers.
problem Breaking security through obscurity in black-box ML settings.
method Zeroth-order optimization for finding universal adversarial perturbations in a black-box setting.
result State-of-the-art ML classifiers can be fooled with a single imperceptible image perturbation.
Bayesian networks with hidden variables help identify causal relationships obscured by confounding.
problem Identifying causal relationships obscured by unobserved confounders.
method Use finite k-mixtures of Bayesian networks with hidden variables to recover the joint probability distribution and identify causal relationships. result First algorithm to learn mixtures of non-empty DAGs, recovering identifiable causal relationships.
The log-periodic power law (LPPL) is a model of asset prices during endogenous bubbles. A major open issue is to verify the presence of LPPL in price sequences and to estimate the LPPL parameters. Estimation is complicated by the fact that daily LPPL returns are typically orders of magnitude smaller than measured price…
New defense method protects client data privacy in federated learning.
problem Gradient leakage attacks in federated learning.
method Learning to obscure data to generate synthetic samples.
result Synthetic samples preserve predictive features and protect privacy.
Frolicher and Nijenhuis recognized well in the middle of the previous century that the Lie bracket and its Jacobi identity could and should exist beyond Lie algebras. Nevertheless the conceptual meaning of their discovery has been obscured by the messy techniques they exploited. The principal objective in this paper is…
We consider the problem of learning the structure of Ising models (pairwise binary Markov random fields) from i.i.d. samples. While several methods have been proposed to accomplish this task, their relative merits and limitations remain somewhat obscure. By analyzing a number of concrete examples, we show that low-comp…
Paper presents techniques to classify UWB SAR imagery, distinguishing targets from clutter.
problem Distinguishing obscured targets from clutter in UWB SAR imagery.
method Three novel sparsity-driven techniques exploiting tensor coefficients and polarization diversity.
result Tensor sparsity models enhance classification accuracy of multi-channel SAR data.
The paper discusses methods to compute Green's function on algebraic surfaces using Schottky uniformization.
problem Computing Green's function on algebraic surfaces using Schottky uniformization.
method Investigates convergence of deformations of a formula related to Green's function.
result Provides insights into the geometric interpretation of the formula for Green's function.
Explains equivariant neural networks for machine learning.
problem Understanding equivariance in neural networks.
method Simple mathematical treatment of neural network concepts.
result Clarifies the mathematical basis of equivariant neural networks.
We consider the problem of learning the structure of Ising models (pairwise binary Markov random fields) from i.i.d. samples. While several methods have been proposed to accomplish this task, their relative merits and limitations remain somewhat obscure. By analyzing a number of concrete examples, we show that low-comp…
The Pinned AUC metric hides unintended bias when class distributions vary.
problem Unintended bias in classification models.
method Examines the Pinned AUC metric and its limitations.
result Pinned AUC can obscure different types of unintended bias.
Study uncovers that loan maturity layers in interbank networks are crucial for understanding their structure and functions.
problem Lack of maturity details in interbank lending networks hinders understanding of network structure and functions.
method Used a complete interbank loan contract dataset and applied the layered stochastic block model to investigate multiple maturity layers.
result Optimal maturity granularity reveals specific economic functions, such as liquidity intermediation and financing.
Recent advances in the understanding of time series permit to clarify seasonalities and cycles, which might be rather obscure in today's literature. A theorem due to P. Cartier and Y. Perrin, which was published only recently, in 1995, and several time scales yield, perhaps for the first time, a clear-cut definition of…
A homology stratification is a filtered space with local homology groups constant on strata. Despite being used by Goresky and MacPherson [Intersection homology theory: II, Inventiones Mathematicae, 71 (1983) 77-129] in their proof of topological invariance of intersection homology, homology stratifications do not appe…
We show that the efficient frontier for a portfolio in which short positions precisely offset the long ones is composed of a pair of straight lines through the origin of the risk-return plane. This unique but important case has been overlooked because the original formulation of the mean-variance model by Markowitz as …
Many applications require the ability to judge uncertainty of time-series forecasts. Uncertainty is often specified as point-wise error bars around a mean or median forecast. Due to temporal dependencies, such a method obscures some information. We would ideally have a way to query the posterior probability of the enti…
Summarizes financial news for better investment decisions.
problem Information overload from financial news hinders timely investment decisions.
method Personalized Chain-of-Thought summarization framework integrating user-specified keywords.
result Personalized summaries highlight relevant market signals, improving investment narratives.
Zap predicts user behavior online using diverse techniques.
problem Predicting user behavior on websites.
method Combines sequential data processing techniques with Bloom filters, bucketing, and model calibration.
result Creates website- and task-specific models without website-specific code.
We generalize the stochastic block model to the important case in which edges are annotated with weights drawn from an exponential family distribution. This generalization introduces several technical difficulties for model estimation, which we solve using a Bayesian approach. We introduce a variational algorithm that …
Anonymization reduces economic signal extraction from financial texts.
problem Reducing meaningful economic signals from financial texts due to anonymization.
method Analyzed the impact of anonymization on textual understanding and economic signal extraction.
result Information loss due to anonymization is severe and pervasive, outweighing its benefits in certain financial applications.
New machine learning model identifies key drivers of market troughs.
problem Misrepresentation of market trough drivers by simpler models.
method Flexible DML average partial effect causal machine learning framework.
result Volatility of options-implied risk appetite and market liquidity are key drivers.
Develops robust methods for computer vision representation learning.
problem Noise and outliers frustrate unsupervised learning of latent representations.
method New robust PCA and spectral clustering methods.
result Superior performance on real-world test sets.
The paper evaluates criteria for selecting cryptocurrencies based on historical data.
problem High risk of cryptocurrencies due to volatility.
method Characterized returns and risks using historical data in short time windows (7 and 15 days). Analyzed the importance of criteria using various methods.
result Importance of criteria for selecting cryptocurrencies is analyzed and evaluated.
Securely trains fair models using homomorphic encryption.
problem Protecting sensitive features while testing model fairness.
method Fully homomorphic encryption for training and testing.
result Practical application to adult income data set.
The classification of isoparametric hypersurfaces with four principal curvatures in the sphere interplays in a deep fashion with commutative algebra, whose abstract and comprehensive nature might obscure a differential geometer's insight into the classification problem that encompasses a wide spectrum of geometry and t…
Smooth parametrization consists in a subdivision of the mathematical objects under consideration into simple pieces, and then parametric representation of each piece, while keeping control of high order derivatives. The main goal of the present paper is to provide a short overview of some results and open problems on s…
We reformulate superalgebra and supergeometry in completely categorical terms by a consequent use of the functor of points. The increased abstraction of this approach is rewarded by a number of great advantages. First, we show that one can extend supergeometry completely naturally to infinite-dimensional contexts. Seco…
Factorization of DE coefficients is violated in antiparallel triple pretzels, but described elegantly.
problem Understanding the origins of factorization in double braids and its extension to antiparallel triple pretzels.
method Defect-preserving deformation from trefoil to antiparallel triple pretzels, analysis of DE coefficients.
result Factorization of DE coefficients is violated but described by an elegant formula for symmetric representations.
Adaptive tensor modeling preserves continuity in multidimensional data.
problem Discretization of continuous multidimensional data loses important information.
method Functional Tucker decomposition (FTD) with RKHS modeling.
result FTD enables adaptive and expressive tensor modeling.
Deep state space model generates text without autoregressive feedback, avoiding biases.
problem Text generation biases and forgetting local nuances.
method Non-autoregressive deep state space model with independent noise and deterministic transition.
result Generative model on par with auto-regressive models, interpretable and without biases.
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.
Algorithm finds causal effects from observational data using auxiliary variables.
problem Estimating causal effects from observational data with confounders.
method Gradient-based optimization using auxiliary variables.
result Algorithm outperforms alternatives in estimating true causal effect.
This paper proposes a new differential privacy definition using Rao distance.
problem Improving differential privacy definitions for better sequential composition.
method Using Rao distance instead of divergences of densities to define privacy.
result Proposed definition shares interpretation with previous definitions but improves sequential composition.
Systems of partial differential equations lie at the heart of physics. Despite this, the general theory of these systems has remained rather obscure in comparison to numerical approaches such as finite element models and various other discretisation schemes. There are, however, several theoretical approaches to systems…
New approach to understand recurrent policies as FSMs without minimization.
problem Minimization of FSMs obscures the semantics of policy decisions.
method Start with unminimized FSM, apply interpretable reductions, use attention tool.
result Reveals insights into policy decisions not previously noticed.
Novel method decomposes EDA signals to reveal user responses.
problem Superposition of noise components obscures EDA signal information.
method Simple pre-processing followed by compressed sensing decomposition.
result Provably accurate recovery of user responses with reduced noise.
Neurons in higher cortical areas, such as the prefrontal cortex, are known to be tuned to a variety of sensory and motor variables. The resulting diversity of neural tuning often obscures the represented information. Here we introduce a novel dimensionality reduction technique, demixed principal component analysis (dPC…
NeuralFLoC unifies registration and clustering of functional data, overcoming phase variation challenges.
problem Challenges in clustering functional data due to phase variation and temporal misalignment.
method NeuralFLoC uses Neural ODE-driven diffeomorphic flows and spectral clustering for joint registration and clustering.
result NeuralFLoC effectively disentangles phase and amplitude variation, achieving state-of-the-art performance.
DiD-BCF model improves causal inference in panel data with robust non-parametric methods.
problem Challenges in Difference-in-Differences (DiD) estimation, especially heterogeneous treatment effects and non-linearities.
method Difference-in-Differences Bayesian Causal Forest (DiD-BCF) with PTA-based reparameterization.
result DiD-BCF provides superior performance and uncovers significant heterogeneity in treatment effects.
Study finds significant price declines and capital reallocation from centralized to decentralized exchanges after FTX collapse.
problem Quantifying trust dynamics and redistribution between centralized and decentralized exchanges.
method Interdisciplinary approach combining causal inference and computational text analysis.
result Significant price declines and capital reallocation from centralized to decentralized exchanges following the FTX collapse.
New framework tackles fairness in link prediction beyond demographic parity.
problem Systemic biases in link prediction can exacerbate societal inequalities.
method Formalizes limitations of existing fairness evaluations and proposes a new framework.
result Proposes a lightweight post-processing method combined with decoupled link predictors.
Financial markets display scale-free behavior in many different aspects. The power-law behavior of part of the distribution of individual wealth has been recognized by Pareto as early as the nineteenth century. Heavy-tailed and scale-free behavior of the distribution of returns of different financial assets have been c…
Paper tackles stochastic reinforcement learning with reduced observation costs.
problem Non-deterministic rewards and punishments with stochastic elements.
method Explicitly models stochastic elements and learning costs.
result Quantitative analysis of learning success criteria and observation cost probabilities.
New method models aptamer libraries as Boltzmann-weighted graph ensembles for better affinity predictions.
problem Anomalous candidates in SELEX datasets obscure true aptamer-ligand affinity.
method Boltzmann graph ensemble embeddings for thermodynamically parameterized exponential-family random graphs.
result Proposed embedding enables robust community detection and subgraph-level explanations for aptamer ligand affinity.
Probabilistic method combines space and time uncertainties in PDEs.
problem Separate treatment of space and time in PDE solvers obscures interactions and error quantification.
method Gaussian process interpretation of finite difference methods interacting with probabilistic ODE solvers.
result Joint quantification of space- and time-uncertainty possible without sacrificing ODE solver performance.