Policy certificates improve reinforcement learning accountability and efficiency.
problem Lack of policy quality information in reinforcement learning algorithms.
method Propose and implement algorithms with policy certificates that bound sub-optimality and return.
result First algorithm achieves minimax-optimal PAC bounds and minimax regret bounds.
Novel framework learns policies for MPC with near-optimal guarantees.
problem Safe and near-optimal policy learning for MPC.
method Primal-dual neural networks for supervised learning of policies and certificate policies.
result Guaranteed feasibility and optimality of learned policies.
Paper certifies neural network control policies against persistent adversarial perturbations.
problem Neural networks' fragility to adversarial perturbations in control systems.
method Combining neural network certification tools with robust control theory.
result Certifies neural network policies in a control loop under l-infinity norm bounded adversarial perturbations.
New reinforcement learning bound improves generalization for sequential data.
problem Challenges in obtaining generalization guarantees for reinforcement learning due to sequential data.
method PAC-Bayesian reinforcement learning with consideration of Markov dependencies and mixing time.
result Demonstrated practical utility through PB-SAC, providing meaningful confidence certificates.
PROWL uses robust reward estimates to improve ITR selection.
problem Reward uncertainty in ITR estimation leads to inflated performance.
method PAC-Bayesian framework with reward uncertainty certificates.
result PROWL achieves better robust treatment regime estimation.
New algorithms learn stability certificates from data, avoiding complex dynamics.
problem Synthesizing stability certificates from complex dynamical systems.
method Developed algorithms to learn certificate functions from trajectory data, establishing generalization error bounds.
result Efficiently learned certificates can be used for adaptive control.
Improved neural network robustness certification through tighter convex relaxations.
problem Certifying neural network robustness to perturbed and adversarial inputs.
method Exploiting ReLU network structure, novel partition-based certification procedure.
result Tightens existing linear programming relaxations to achieve zero relaxation error asymptotically.
The study improves off-policy learning by smoothing IPS and provides a generalization bound.
problem Improving off-policy learning from logged bandit data.
method Smooth regularization for IPS, deriving a two-sided PAC-Bayes generalization bound.
result The bound is valid for standard IPS and provides insights into when regularization is useful.
The paper optimizes policies constrained to Schur stabilizing controllers using a Newton-type algorithm.
problem Optimizing policies under linear constraints in control systems.
method Newton-type algorithm on a manifold of Schur stabilizing controllers with a Riemannian metric.
result Local convergence guarantees for the Newton-type algorithm without relying on exponential mapping or retractions.
The paper introduces robustness certificates for ReLU networks to protect against adversarial perturbations.
problem The vulnerability of ReLU networks to small adversarial perturbations.
method The paper proposes two lower bounds for the distance of a given input sample to the classification decision boundary of a ReLU network.
result The proposed simplex certificate is a closed-form, differentiable, and computationally efficient robustness measure.
Develops structured noise for more accurate graph classifier robustness certificates.
problem Isotropic noise limits robustness certificates for graph classifiers.
method Randomized smoothing with anisotropic noise distribution.
result Structured-aware robustness certificates provide more accurate predictions.
New method closes certification gap for adversarially trained models.
problem Certifying robustness of adversarially trained neural networks.
method Nonconvex low-rank SDP relaxation with polynomial-time optimization.
result Strong certifications comparable to SDP methods, but with fewer variables.
New method estimates policy performance under unobserved confounding.
problem Estimating policy performance when decisions depend on unobserved variables.
method Developed worst-case bounds for robust OPE under unobserved confounding.
result Efficient procedure for computing worst-case bounds, proving statistical consistency.
New framework improves adversarial robustness certification for various perturbations.
problem Certifying robustness against adversarial attacks in deep learning models.
method Unified functional optimization approach with non-Gaussian smoothing noise for multiple types of attacks.
result Achieves better certification results and identifies key trade-offs between accuracy and robustness.
Bayesian method synthesizes barrier certificates for unknown systems with latent states.
problem Certifying safety in systems with unknown dynamics and latent states.
method Bayesian inference with Metropolis-Hastings sampler and sum-of-squares program.
result Probabilistic validity of barrier certificates for unknown systems.
CITE algorithm provides anytime-valid certification of model outputs.
problem Challenges in controlling error levels in LLM self-consistency.
method Certification by Intersection-union Testing with E-processes (CITE) algorithm.
result Provable control of false certification at any prescribed level under arbitrary stopping rules.
Paper develops tighter risk certificates for contrastive learning models.
problem Statistical theory for contrastive learning is lacking, especially for practical models like SimCLR.
method Develops non-vacuous PAC-Bayesian risk certificates considering practical SimCLR factors.
result Risk certificates for contrastive loss and downstream prediction are much tighter than previous results.
Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world systems. As a consequence, learning algorithms are rarely applied on safety-crit…
Develops local population-risk certificates for model updates
problem Model updates in machine learning
method Certify population-risk increments around a model
result Certified upper endpoint yields a risk-controlled update rule
New method provides tighter robustness guarantees for adversarial attacks.
problem Ensuring robustness against adversarial attacks in machine learning models.
method Developed a Second-order Smoothing (SoS) robustness certificate using Gaussian random smoothing.
result SoS certificates are tighter and provide improved robustness on high-dimensional datasets.
TUV Austria proposes certification for ML applications to ensure reliability.
problem Ensuring trust in AI applications to meet societal reliance requirements.
method Holistic approach analyzing security, functionality, data quality, ethics, and criticality levels.
result Certification process for low-risk ML applications in supervised learning.
Valid certifies LLMs' domain adherence, bounding out-of-domain behavior.
problem Adversarial susceptibility of LLMs to generate out-of-domain outputs.
method VALID approach providing adversarial bounds as a certificate.
result Validates LLMs' domain adherence with meaningful certificates.
Paper provides efficient robustness certificates for neural networks.
problem Ensuring neural networks are robust against adversarial attacks.
method Two-step approach: 1) Efficient convex optimization for robustness certificates with bounded Hessian eigenvalues, 2) Curvature-based regularization during training.
result Significantly higher certified robust accuracy achieved compared to existing methods.
New attack tricks certifiably robust models into mislabeling images.
problem Defeating certified defenses against adversarial examples.
method Spoofed robustness certificates and large perturbations.
result Certifiably robust models can be fooled by large perturbations.
Conformal Candidate Certification advances offline MBO by certifying candidate designs with statistical guarantees.
problem Offline model-based optimization
method Conformal Candidate Certification (CCC)
result CCC certifies 16.7% of an aggressive proposal pool with 0.990 empirical coverage at nominal 0.90.
New robustness certificates for streaming models with a sliding window.
problem Applying robustness certificates to streaming data with correlated inputs.
method Deriving robustness certificates for models using a sliding window over a sequence of potentially correlated inputs.
result Guarantees hold for the average model performance across the entire stream, independent of stream size.
Survey examines challenges of ML in avionic systems certification.
problem Challenges in current certification standards for ML in avionic systems.
method Literature review focusing on robustness and explainability of ML results.
result Current certification standards do not support ML in avionic systems.
Geometric technique determines exactness of SDP robustness certificate.
problem Certifying robustness of neural networks to adversarial examples.
method Geometric projection onto hyperbola, SDP relaxation of ReLU activation.
result SDP certificate is exact for a single hidden layer under mild assumptions.
This work improves deep reinforcement learning robustness to adversarial state uncertainty.
problem Robustness of deep reinforcement learning to adversarial state uncertainty.
method Certified adversarial robustness techniques are applied to deep reinforcement learning algorithms to compute guaranteed lower bounds on state-action values.
result The approach increases robustness to noise and adversaries in pedestrian collision avoidance and classic control tasks.
The paper improves risk certificate tightness for neural networks using PAC-Bayes bounds.
problem Improving the usability of risk certificates for neural networks based on PAC-Bayes bounds.
method Theoretical contributions including KL divergence bounds, efficient methodology for optimization, and methods for optimizing non-differentiable objectives.
result First non-vacuous generalization bounds on CIFAR-10 for neural networks.
Study adversarial perturbations in classification, analyzing learning and certification.
problem Formal study of classification under adversarial perturbations from both learner and third-party perspectives.
method PAC-type semi-supervised learning framework, black-box certification under limited query budget, adversary analysis.
result Existence of a polynomial query complexity adversary implies the existence of a sample efficient robust learner.
New method improves robustness of smoothed classifiers against adversarial attacks.
problem Improving robustness of smoothed classifiers against adversarial attacks.
method Proposes worst-case adversarial loss over input distributions as a robustness certificate, and uses duality and smoothness properties to provide an easy-to-compute upper bound.
result Shows superior robustness performance over state-of-the-art certified or heuristic methods.
New framework certifies robustness for regression models.
problem Certifying robustness for regression models is challenging.
method Derives a prediction-centered certificate that exploits local geometry.
result Gradient information yields tighter robustness certificates.
This paper develops a general theoretical framework to analyze structured sparse recovery problems using the notation of dual certificate. Although certain aspects of the dual certificate idea have already been used in some previous work, due to the lack of a general and coherent theory, the analysis has so far only be…
Given a tame knot K presented in the form of a knot diagram, we show that the problem of determining whether K is knotted is in the complexity class NP, assuming the generalized Riemann hypothesis (GRH). In other words, there exists a polynomial-length certificate that can be verified in polynomial time to prove that K…
New method certifies robustness to sparse adversarial attacks.
problem Ensuring robustness of classifiers to sparse adversarial attacks.
method Randomized ablation of input features to provide robustness guarantees.
result Certifies robustness to sparse adversarial attacks with up to 31 pixels of distortion.
Optimal solar energy production and trading strategies in SREC markets identified.
problem Optimizing solar energy production and trading in SREC markets.
method Formulated a stochastic control problem, accounting for generation and trading costs, and developed a numerical algorithm to solve the control problem.
result An optimal firm's generation and trading behavior can be separated into various regimes based on the marginal benefit of obtaining an additional SREC.
Study predicts dropout and certification in MOOCs using student logs and forum data.
problem Predicting attrition and certification in MOOCs.
method Survival analysis, feature selection, and model evaluation.
result Identifies relevant features for predicting dropout and certification.
New method defends against patch attacks with high-certainty guarantees.
problem Patch attacks on images, especially physical adversarial attacks.
method Randomized smoothing, exploiting patch constraints.
result Meaningfully large robustness certificates against patch attacks.
Study predicts infant mortality using birth certificate data.
problem High infant mortality rate in the U.S. and racial/ethnic disparities.
method Classification models trained on birth certificate features.
result Methodology outperforms standard classification methods.
The paper compares machine learning methods with traditional techniques for pricing and sensitivities of financial products with path-dependent structures.
problem Evaluating financial products with early-termination clauses, especially those with path-dependent structures.
method The paper compares regression methods including randomized recurrent and feed-forward neural networks, and a novel approach using signatures of the underlying price process, with traditional polynomial basis functions for pricing and sensitivities.
result Machine learning algorithms often match the accuracy and efficiency of traditional methods for Asian and look-back options, while randomized neural networks are best for callable certificates.
New method certifies deep graph classifiers with tighter risk bounds.
problem Certifying the reliability of deep graph classifiers.
method Linearized deep assignment flows with random initial conditions, using PAC-Bayes risk certification.
result Computes tighter out-of-sample risk certificates efficiently.
Develops certificates for local population-risk increments using cross-fitted ridge calibration.
problem Certifying local population-risk increments in statistical models.
method Cross-fitted ridge calibration for linear feature classes, separating Taylor fluctuations and remainders.
result Certifies measurable updates from the same sample with penalties dependent on empirical geometry.
Deep learning improves death cause coding accuracy.
problem Geospatial discrepancies in human-coded death certificates.
method Deep artificial neural network model trained on CépiDc database.
result 97.8% accuracy in automated coding compared to 75% for Iris software.
The paper proposes trading grades in a financial market to address unintended consequences of grading systems.
problem Unintended consequences of grading systems, such as unfair advantages and misaligned incentives.
method A thought experiment in a financial market structure to trade grades, similar to interest rate swaps.
result Grades should be viewed as personal equity, not used for selection criteria.
Develops optimal decision-making framework for uncertain counterfactuals.
problem Ensuring reliability of predictions in high-stakes decisions.
method Policy-Coupled Risk-Averse Conformal Prediction (PC-RACP).
result Optimal prediction sets for counterfactual decisions with valid coverage.
New method improves robustness of smoothed classifiers.
problem Improving accuracy and robustness of smoothed classifiers.
method Regularized risk with adaptive regularization.
result Tighter robustness bounds with high probability.
Study certifies missed relevant items in candidate generation with audit labels.
problem Certify missed relevant items in candidate generation with audit labels.
method Characterizes label complexity, develops exact finite-sample toolkit.
result Excluded-pool auditing is minimax rate-optimal for missed-mass certification.