On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

← all fields·11 papers on “robustness” in Statistical ML · 1 month

On the Role of Normalization in Binary Iterative Hard Thresholding for 1-bit Compressed Sensingcs.IT

This paper resolves BIHT convergence, showing normalization is not necessary in noiseless settings but crucial for robustness.

problem Analyzing convergence and robustness of BIHT for 1-bit compressed sensing.

method Characterizes BIHT convergence and robustness, proving necessity of normalization for robustness under sign corruptions.

result Per-iteration normalization is not necessary for optimal recovery in noiseless settings but is crucial for robustness under sign corruptions.

BIHT 1-bit compressed sensing convergence analysis robustness normalization

2026-07-17abs ↗pdf ↗

Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detectionstat.ML

New metrics fail adversarial tests, with some more robust than others.

problem Evaluation metrics for time-series anomaly detection were improved but not fully robust.

method Adversarial stress-testing of 12 adopted metrics on real benchmarks.

result Some metrics are more robust than others, with ROC-based metrics being gamed more often.

time-series anomaly detection evaluation metrics adversarial testing robustness metrics comparison

2026-07-12abs ↗pdf ↗

A law of robustness for two-layer neural networks with arbitrary weightscs.LG

Two-layer neural networks must be robust, even with arbitrary weights.

problem Proving the robustness of two-layer neural networks with arbitrary weights.

method Developed a new function-space covering method to prove the robustness law, replacing parameter-space covering.

result Proved the conjectured law for two-layer networks with arbitrary real weights, biases, and affine skip connections.

Neural Networks Robustness Two-Layer Networks Arbitrary Weights Activation Functions

2026-07-08abs ↗pdf ↗

LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networkscs.LG

LiST improves neural network robustness and calibration without manual tuning.

problem Developing robust and calibrated neural networks simultaneously.

method Lipschitz Scaling Training (LiST) that iteratively adjusts the global Lipschitz constant.

result LiST yields an out-of-the-box calibrated network with competitive accuracy and robustness.

Lipschitz scaling neural networks robustness calibration Temperature Scaling

2026-07-08abs ↗pdf ↗

Robust Bayes-Assisted Conformal Predictionstat.ML

Robust Bayes-Assisted Conformal Prediction improves prediction set sizes.

problem Misspecification of Bayesian working model and prior misalignment.

method RoBAS (Robust Bayes-Assisted Shrinkage) framework with two instantiations.

result Improves prediction set sizes in shifted settings.

Bayesian Conformal Prediction Robustness Shrinkage Tabular Data

2026-07-05abs ↗pdf ↗

Robust Bayes-Assisted Conformal Predictionstat.ML

Robust Bayes-Assisted Conformal Prediction improves prediction set sizes.

problem Misspecification of Bayesian working model and prior misalignment.

method RoBAS (Robust Bayes-Assisted Shrinkage) framework with two instantiations.

result Proposed scores adapt to prior quality, reducing interval widths in shifted settings.

Bayesian Conformal Prediction Robustness Shrinkage Nonconformity Scores

2026-07-05abs ↗pdf ↗

Fast SDP certification of neural networks : towards large multi-class datasetsmath.CO

New SDP method certifies neural network robustness across all classes efficiently.

problem Certifying robustness of neural networks across multiple classes.

method Quadratic model + SDP relaxation + pruning strategy.

result Significant computational speed-up and scalability to large datasets.

neural networks robustness SDP quadratic model pruning

2026-07-03abs ↗pdf ↗

OpFlow: Learning Opportunity-Conditioned Choice Potentials for Robust OD Flow Predictioncs.LG

OpFlow predicts robust OD flows by learning choice potentials conditioned on spatial exposures.

problem Deep models trained on raw counts are vulnerable to distribution shift.

method OpFlow learns row-centered choice potentials and reconstructs flows by combining them with a calibrated origin scale.

result OpFlow improves robustness under environment shifts, as shown by controlled synthetic shifts and a real-world experiment.

OpFlow OD flow prediction robustness choice potentials spatial exposures

2026-07-03abs ↗pdf ↗

Contaminated Multi-task Learning with Heterogeneity: Fundamental Limits and Optimal Algorithmsstat.ML

Study tackles contamination and heterogeneity in multi-task learning, improving robustness and personalization.

problem Challenges in integrating related tasks due to contamination and heterogeneity.

method Proposes a filtering-based robust multi-task gradient descent method to estimate global and clean task-specific minimizers.

result Demonstrates improved robustness and personalization compared to existing methods.

multi-task learning contamination heterogeneity robustness personalization

2026-07-02abs ↗pdf ↗

From Approximation to Emergence: A Theory of Deep Learningcs.LG

Unified theory of deep learning from approximation to emergence.

problem Understanding the mechanisms behind deep learning.

method Unified, proof-oriented approach tracing from classical foundations to contemporary mechanisms.

result Unified theory explaining deep learning from approximation to emergence.

deep learning approximation theory generalization overparameterization robustness

2026-07-01abs ↗pdf ↗

Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimizationcs.LG

A new method for optimizing hierarchical multi-objective problems.

problem Symmetry and neglect of objective hierarchy in existing multi-objective methods.

method Priority-Constrained Descent (PCD) framework exploiting hierarchical objective structures.

result Pareto dominance and better per-objective performance with secondary progress guarantees.

multi-objective optimization hierarchical objectives priority-constrained descent sparsity compression

2026-06-28abs ↗pdf ↗