{"total":52,"rows":[{"id":"2108.12515","title":"Convergence Rates for Learning Linear Operators from Noisy Data","created":"2021-08-27","cited_by_count":55,"area":null},{"id":"2207.06415","title":"The Free Energy Principle for Perception and Action: A Deep Learning Perspective","created":"2022-07-13","cited_by_count":24,"area":null},{"id":"2206.14373","title":"Theoretical Perspectives on Deep Learning Methods in Inverse Problems","created":"2022-06-29","cited_by_count":22,"area":null},{"id":"2306.12213","title":"Limits for Learning with Language Models","created":"2023-06-21","cited_by_count":17,"area":null},{"id":"2109.06098","title":"The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks","created":"2021-09-13","cited_by_count":16,"area":null},{"id":"2106.13997","title":"The Feasibility and Inevitability of Stealth Attacks","created":"2021-06-26","cited_by_count":12,"area":null},{"id":"2205.14630","title":"Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)","created":"2022-05-29","cited_by_count":10,"area":null},{"id":"2202.13490","title":"Limitations of Deep Learning for Inverse Problems on Digital Hardware","created":"2022-02-28","cited_by_count":9,"area":null},{"id":"2203.13908","title":"On efficient algorithms for computing near-best polynomial approximations to high-dimensional, Hilbert-valued functions from limited samples","created":"2022-03-25","cited_by_count":8,"area":null},{"id":"2211.13692","title":"To be or not to be stable, that is the question: understanding neural networks for inverse problems","created":"2022-11-24","cited_by_count":8,"area":null},{"id":"2303.15385","title":"Recognizing Rigid Patterns of Unlabeled Point Clouds by Complete and Continuous Isometry Invariants with no False Negatives and no False Positives","created":"2023-03-27","cited_by_count":8,"area":null},{"id":"2311.17350","title":"Implicit-explicit Integrated Representations for Multi-view Video Compression","created":"2023-11-29","cited_by_count":8,"area":null},{"id":"2404.03761","title":"Learning smooth functions in high dimensions: from sparse polynomials to deep neural networks","created":"2024-04-04","cited_by_count":7,"area":null},{"id":"2207.01466","title":"Physics-informed compressed sensing for PC-MRI: an inverse Navier-Stokes problem","created":"2022-07-04","cited_by_count":6,"area":null},{"id":"2401.00816","title":"Glimpse: Generalized Locality for Scalable and Robust CT","created":"2024-01-01","cited_by_count":6,"area":null},{"id":"2203.00804","title":"NESTANets: Stable, accurate and efficient neural networks for analysis-sparse inverse problems","created":"2022-03-02","cited_by_count":5,"area":null},{"id":"2212.06370","title":"Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation","created":"2022-12-13","cited_by_count":5,"area":null},{"id":"2301.06148","title":"Computability of Optimizers","created":"2023-01-15","cited_by_count":5,"area":null},{"id":"2310.18702","title":"Towards Combinatorial Generalization for Catalysts: A Kohn-Sham Charge-Density Approach","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2408.02357","title":"On the consistent reasoning paradox of intelligence and optimal trust in AI: The power of 'I don't know'","created":"2024-08-05","cited_by_count":5,"area":null},{"id":"2205.01493","title":"On the uncertainty principle of neural networks","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2307.07410","title":"Implicit regularization in AI meets generalized hardness of approximation in optimization -- Sharp results for diagonal linear networks","created":"2023-07-13","cited_by_count":4,"area":null},{"id":"2402.10983","title":"Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks","created":"2024-02-16","cited_by_count":4,"area":null},{"id":"2406.18464","title":"Bayesian inverse Navier-Stokes problems: joint flow field reconstruction and parameter learning","created":"2024-06-26","cited_by_count":4,"area":null},{"id":"2206.00934","title":"Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems","created":"2022-06-02","cited_by_count":3,"area":null},{"id":"2302.11446","title":"Singular value decomposition based matrix surgery","created":"2023-02-22","cited_by_count":3,"area":null},{"id":"2201.08652","title":"A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks","created":"2022-01-21","cited_by_count":2,"area":null},{"id":"2206.05289","title":"Localized adversarial artifacts for compressed sensing MRI","created":"2022-06-10","cited_by_count":2,"area":null},{"id":"2210.00805","title":"Limitations of neural network training due to numerical instability of backpropagation","created":"2022-10-03","cited_by_count":2,"area":null},{"id":"2301.02268","title":"Restarts subject to approximate sharpness: A parameter-free and optimal scheme for first-order methods","created":"2023-01-05","cited_by_count":2,"area":null},{"id":"2303.08587","title":"Delay-SDE-net: A deep learning approach for time series modelling with memory and uncertainty estimates","created":"2023-03-14","cited_by_count":2,"area":null},{"id":"2309.01796","title":"Implicit Regularization Makes Overparameterized Asymmetric Matrix Sensing Robust to Perturbations","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2312.11425","title":"When can you trust feature selection? -- I: A condition-based analysis of LASSO and generalised hardness of approximation","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2401.07874","title":"Do stable neural networks exist for classification problems? -- A new view on stability in AI","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2505.10630","title":"How many measurements are enough? Bayesian recovery in inverse problems with general distributions","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2505.15661","title":"Deep greedy unfolding: Sorting out argsorting in greedy sparse recovery algorithms","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2601.22763","title":"Is Task-Specific Training Necessary for Anomaly Detection?","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2110.12437","title":"WARPd: A linearly convergent first-order method for inverse problems with approximate sharpness conditions","created":"2021-10-24","cited_by_count":1,"area":null},{"id":"2112.12275","title":"A Simplicity Bubble Problem in Formal-Theoretic Learning Systems","created":"2021-12-22","cited_by_count":1,"area":null},{"id":"2202.06242","title":"Beyond NaN: Resiliency of Optimization Layers in The Face of Infeasibility","created":"2022-02-13","cited_by_count":1,"area":null},{"id":"2308.16754","title":"Training Neural Networks Using Reproducing Kernel Space Interpolation and Model Reduction","created":"2023-08-31","cited_by_count":1,"area":null},{"id":"2401.10310","title":"Mathematical Algorithm Design for Deep Learning under Societal and Judicial Constraints: The Algorithmic Transparency Requirement","created":"2024-01-18","cited_by_count":1,"area":null},{"id":"2402.00899","title":"Weakly Supervised Learners for Correction of AI Errors with Provable Performance Guarantees","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2408.12273","title":"Geometrical structures of digital fluctuations in parameter space of neural networks trained with adaptive momentum optimization","created":"2024-08-22","cited_by_count":1,"area":null},{"id":"2207.08137","title":"Achieve Optimal Adversarial Accuracy for Adversarial Deep Learning using Stackelberg Game","created":"2022-07-17","cited_by_count":0,"area":null},{"id":"2303.03678","title":"A Comparative Study of Deep Learning and Iterative Algorithms for Joint Channel Estimation and Signal Detection in OFDM Systems","created":"2023-03-07","cited_by_count":0,"area":null},{"id":"2408.06212","title":"Computability of Classification and Deep Learning: From Theoretical Limits to Practical Feasibility through Quantization","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2505.14424","title":"Explaining Neural Networks with Reasons","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2505.17254","title":"Approach to Finding a Robust Deep Learning Model","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2508.14118","title":"Hallucinations in medical devices","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2602.18536","title":"Triggering hallucinations in model-based MRI reconstruction via adversarial perturbations","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2605.13146","title":"On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods","created":"2026-05-13","cited_by_count":0,"area":null}],"next_cursor":null}