The paper proposes a tool to detect invalid inputs in DL models.
problem Vulnerability of DL models to invalid inputs during runtime.
method Design and implementation of a tool that extracts data flow footprints and conducts assertion-based validation.
result The assertion-based data sanity check mechanism effectively identifies invalid input cases.
Recourse explanations can become invalid if collective actions change statistical data.
problem Recourse explanations may become invalid due to collective behavior changing data statistics.
method Formal characterization of conditions under which recourse explanations remain valid under performativity.
result Recourse actions may become invalid if they are influenced by or intervene on non-causal variables.
The paper investigates the effects of invalid action masking in policy gradient algorithms.
problem Invalid actions in policy gradient algorithms can lead to suboptimal performance.
method The paper provides theoretical justification and empirical demonstrations of the importance of invalid action masking.
result Invalid action masking is crucial as the number of invalid actions increases.
TSCI estimates treatment effects using machine learning and data-adaptive methods for invalid instruments.
problem Estimating treatment effects with invalid instruments.
method Two-stage algorithm: first stage uses machine learning for nonlinearities, second stage selects and projects out instrument violations.
result Effective treatment effect estimation even with invalid instruments.
MINs learn inverse mappings for high-dimensional optimization problems.
problem Data-driven optimization with high-dimensional inputs and valid subsets.
method Model Inversion Networks (MINs) learn an inverse mapping from scores to inputs.
result MINs can scale to high-dimensional input spaces and handle both offline and active data.
A generative model may generate utter nonsense when it is fit to maximize the likelihood of observed data. This happens due to "model error," i.e., when the true data generating distribution does not fit within the class of generative models being learned. To address this, we propose a model of active distribution lear…
New method for personalized pricing using invalid instrumental variables.
problem Personalized pricing under endogeneity with limited standard methods.
method PRINT method for continuous treatment, solving conditional moment restrictions.
result Established optimal pricing strategy under endogeneity with invalid instrumental variables.
Symbolic knowledge in neural models can inadvertently make them more vulnerable to adversarial attacks.
problem Symbolic knowledge in neural models can make models more susceptible to adversarial attacks.
method Investigated deep probabilistic graphical models that incorporate symbolic knowledge and neural nets.
result Symbolic knowledge can propagate the negative effects of adversarial examples, making models more vulnerable.
New method identifies valid IVs for bi-directional MR with invalid instruments.
problem Estimating causal effects from observational data with invalid instruments and unmeasured confounding.
method Theoretical investigation and cluster fusion-like method to discover valid IV sets.
result Theoretical demonstration and experimental validation of the method's effectiveness.
Invalidation of a key lemma leaves the Powell Conjecture unresolved.
problem Invalidation of Lemma 2.5 in the Powell Conjecture proof.
method Analysis of Lemma 2.5's validity in the context of the Powell Conjecture.
result Lemma 2.5 is invalid, leaving the Powell Conjecture unresolved.
Paper extends Bayes Theorem for interval probability estimates.
problem Real-world input probabilities are often interval estimates, not precise.
method Developed IT2 version of Bayes Theorem and a novel algorithm for encoding intervals.
result Conservative method avoids invalid output results from inconsistent input.
Parameterised actions in reinforcement learning are composed of discrete actions with continuous action-parameters. This provides a framework for solving complex domains that require combining high-level actions with flexible control. The recent P-DQN algorithm extends deep Q-networks to learn over such action spaces. …
Proposes TSCI method to infer causal effects with weak or invalid instruments using machine learning.
problem Causal inference with weak or invalid instrumental variables.
method Two-stage curvature identification (TSCI) using machine learning.
result Asymptotically unbiased and Gaussian estimator for causal effects.
Deep learning techniques have been hugely successful for traditional supervised and unsupervised machine learning problems. In large part, these techniques solve continuous optimization problems. Recently however, discrete generative deep learning models have been successfully used to efficiently search high-dimensiona…
There is an error in the proof of Theorem 1.1 that invalidates proofs of other theorems. Theorem 1.5 is unaffected.
CV inference can be invalid for relatively unstable model comparisons.
problem The validity of cross-validation for model comparison is questioned when models are relatively unstable.
method The study proves that simple, individually stable models can generate relatively unstable comparisons, invalidating CV inference.
result The Lasso and soft-thresholding generate relatively unstable comparisons, invalidating CV inferences.
Robust OPE framework uses human inputs to improve policy evaluation in changing environments.
problem Inaccurate policy evaluations due to shifts in environment properties.
method Adapts OPE methods to shifts on user-inputted covariates, providing more realistic utility estimates.
result Robust OPE framework yields less pessimistic policy evaluations and captures realistic dataset shifts.
AI-generated variables bias regression estimates; methods correct for invalid inference.
problem Bias in regression estimates due to AI-generated variables.
method Two methods: bias correction and joint estimation.
result Valid inference restored through proposed methods.
New method prevents invalid inference after causal discovery.
problem Invalid inference after causal discovery.
method Developed tools for valid post-causal-discovery inference.
result Our method provides reliable coverage while achieving more accurate causal discovery.
Karl Menger's 1934 paper on the St. Petersburg paradox contains mathematical errors that invalidate his conclusion that unbounded utility functions, specifically Bernoulli's logarithmic utility, fail to resolve modified versions of the St. Petersburg paradox.
Benchmark evaluates financial misinformation detection models, revealing weaknesses without external context.
problem Detecting financial misinformation without external references.
method RFC Bench at paragraph level, two tasks: reference-free detection and comparison-based diagnosis.
result Performance improves with comparative context, revealing model weaknesses in reference-free settings.
We propose a simple change to existing neural network structures for better defending against gradient-based adversarial attacks. Instead of using popular activation functions (such as ReLU), we advocate the use of k-Winners-Take-All (k-WTA) activation, a C0 discontinuous function that purposely invalidates the neural …
New findings on mesh group-planes validate Signature-inverse Theorem under specific conditions.
problem Invalidity of existing inverse theorems for mesh group-planes.
method Classification of three and five point meshes, analysis of joint invariant signatures.
result Valid conditions for the Signature-inverse Theorem in mesh group-planes.
The paper addresses uncertainties in spectral clustering of corrupted data.
problem Uncertainties in spectral clustering due to measurement errors and missing data.
method Mathematical framework based on random set theory for Monte Carlo approximation of expected clusterings.
result Consistent quantities of interest for evaluating clusterings in corrupted data.
New method improves IV estimation with many weak and invalid instruments.
problem Identification in linear IV models with unknown validity.
method Non-convex penalized approaches, surrogate sparsest penalty.
result Advantages over other IV estimators in selection consistency and weak IV strength conditions.
Complex embeddings handle non-metric proximity data better than traditional methods.
problem Proximities not always metric or inner product-based, causing convergence issues.
method Proposes complex-valued embeddings for non-vectorial data.
result Complex embeddings outperform traditional techniques on benchmarks.
The paper studies how to use AI-generated labels in econometrics to avoid bias.
problem Small misclassification errors in AI-generated labels can lead to large biases in econometric estimators.
method The paper proposes a coupled-label bootstrap method to correct bias and deliver valid inference.
result The coupled-label bootstrap method is valid without the strong independence condition between true and imputed labels.
Deep generative models have been successfully used to learn representations for high-dimensional discrete spaces by representing discrete objects as sequences and employing powerful sequence-based deep models. Unfortunately, these sequence-based models often produce invalid sequences: sequences which do not represent a…
To collectively forecast the demand for ride-sourcing services in all regions of a city, the deep learning approaches have been applied with commendable results. However, the local statistical differences throughout the geographical layout of the city make the spatial stationarity assumption of the convolution invalid,…
AVATAR uses a surrogate model to quickly evaluate ML pipelines, saving time and resources.
problem Time-consuming evaluation of ML pipelines limits exploration of complex models.
method AVATAR employs a surrogate model to assess pipeline validity without execution.
result AVATAR accelerates ML pipeline evaluation, improving efficiency in complex scenarios.
Paper finds previous work on submanifolds incorrect.
problem Incorrect definition of semi-invariant submanifolds.
method Examined previous work's definition and found it flawed.
result Previous results on semi-invariant submanifolds are invalid.
Improves statistical inference using machine learning predictions with imputed data.
problem Invalid statistical inference due to machine learning prediction errors.
method Bootstrap confidence intervals for nonuniform samples and arbitrary imputed features.
result Valid confidence intervals without assumptions on machine learning model quality.
Ivy combines weak IV candidates to estimate causal effects robustly.
problem Estimating causal effects from observational data using weak or invalid IV candidates.
method Ivy synthesizes multiple weak IV candidates into a robust summary.
result Ivy produces more reliable causal effect estimates compared to allele scores.
Deep RL learns to construct objects from 2D images by avoiding brick overlaps.
problem Learning to construct objects from partial 2D images with constraints.
method Combination of reinforcement learning and action validity prediction.
result Successfully constructs unseen objects from 2D images.
Valid causal inference with invalid instruments using majority or modal valid relationships.
problem Estimating causal effects in the presence of unobserved confounding and invalid instruments.
method Ensemble of instrumental variable estimators to estimate the modal prediction, achieving accurate estimates of conditional average treatment effects.
result Valid causal inference can be achieved with a majority or modal valid instrument-response relationship.
This paper examines the assumptions of the derived equivalence between dropout noise injection and L2 regularisation for logistic regression with negative log loss. We show that the approximation method is based on a divergent Taylor expansion, making, subsequent work using this approximation to compare the dropout …
We give a construction to remove coincidence points of continuous maps on graphs (1-complexes) by changing the maps by homotopies. When the codomain is not homeomorphic to the circle, we show that any pair of maps can be changed by homotopies to be coincidence free. This means that there can be no nontrivial coincidenc…
RPN 2 improves function learning by modeling data interdependence.
problem Invalid assumption of input data independence leads to performance degradation.
method Integrates data and structural interdependence functions into RPN 2's architecture.
result Significantly improves learning performance and expands unifying potential.
In a recent paper, "Why does deep and cheap learning work so well?", Lin and Tegmark claim to show that the mapping between deep belief networks and the variational renormalization group derived in [arXiv:1410.3831] is invalid, and present a "counterexample" that claims to show that this mapping does not hold. In this …
We address challenges of active learning under scarce informational resources in non-stationary environments. In real-world settings, data labeled and integrated into a predictive model may become invalid over time. However, the data can become informative again with switches in context and such changes may indicate un…
A stability-based method selects the most desirable conformal prediction set.
problem Selecting the most desirable conformal prediction set from multiple valid sets invalidates coverage guarantees.
method A stability-based approach that ensures coverage for the selected prediction set.
result The stability-based approach maintains coverage guarantees for the selected prediction set.
A method to detect spillover effects and select valid donors for synthetic control models.
problem Identifying valid donors in synthetic control models when spillover effects are possible.
method Theoretical grounding and practical method using pre-intervention data to identify donor values and debias causal estimates.
result A Theorem that identifies assumptions for identifying donor values and debias causal estimates.
CONTINA provides adaptive confidence intervals for traffic demand prediction.
problem Uncertainty in future traffic demand predictions and the need for valid confidence intervals.
method Adaptive confidence interval method that adjusts based on deployment errors.
result Valid confidence intervals with shorter lengths and theoretical coverage guarantee.
Hybrid deep learning algorithm optimizes register allocation for compiler.
problem Efficiently coloring interference graphs for register allocation.
method Deep learning network trained on random graphs, augmented with a color correction phase.
result Hybrid algorithm performs well compared to optimal and greedy register allocators.
Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant. In such cases, it is sometimes easier to learn which actions not to take. In this work, we propose the Action-Elimination…
Method selects valid IVs from a large set using clustering and test of overidentifying restrictions.
problem Selecting valid instrumental variables from a large set of candidates.
method Agglomerative hierarchical clustering combined with a test of overidentifying restrictions.
result Achieves oracle properties when the largest group of IVs is valid.
The paper examines the stability of Minkowski inequality for nearly spherical domains.
problem Stability of Minkowski inequality for nearly spherical domains.
method Analyzes stability inequalities for C1 perturbations of a ball and axially symmetric perturbations. result Established stability inequalities for curvature integrals of nearly spherical domains.
K-fold cross-validation (CV) with squared error loss is widely used for evaluating predictive models, especially when strong distributional assumptions cannot be taken. However, CV with squared error loss is not free from distributional assumptions, in particular in cases involving non-i.i.d. data. This paper analyzes …