Learning angles for quantum approximate optimization
Learned models predict high-quality QAOA angles in one pass, matching slower per-instance solvers.
Stories per day · 30 days
9 RSS
Relatedarxiv1backdoor1bias-correction1combinatorial-optimization1data-augmentation1data-sanitization1ecmwf1ids1intrusion-detection1latent-space1malware-detection1microsoft1nature1open-source1phantomware1poisoning1qaoa1quantum-computing1
87 stories, newest first · one card per story
Stories tagged #machine-learning
Phantomware: a Data Augmentation Framework for the Detection of Emerging Malware Campaigns
Phantomware augments scarce malware training data in latent space to detect unseen variants.
Microsoft has a new machine learning tool to improve weather forecasts
Microsoft open-sourced Probabilistic Bias Correction, a CPU-friendly method that improves forecasts two to six weeks ahead.
2
Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection
Researchers backdoor flow-based IDS models with 0.001% poisoned data and propose mitigations.
Decision-Focused Learning for Cyber-Physical Risk-Aware Power Grid Operations
Researchers tie grid intrusion-detection errors to operational cyber-physical costs via decision-focused learning.
One Thing Leads to Another: The Essentials of Time Series Causal Discovery
A tutorial unifies time-series causal discovery methods, assumptions, evaluation, and uses in science, healthcare, and AI.
Better Batches, Better Privacy: Random Allocation for DP-BandMF
Random-allocation batching for DP-BandMF cuts RMSE up to 1.85 times and speeds privacy accounting on GPUs.
Predicting Cable Dynamics with Physical Attention Bias
Physical attention bias using cable geometry improves long-horizon prediction of unseen cable motion.
Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion
Corrected two-level softmax samplers remove cluster-size and dispersion bias with little overhead.
PairAudit: Guiding Human Review with Graph Tokens under Distribution Shift
PairAudit uses graph tokens to surface overlooked intrusion-detector mistakes and improve fixed-budget review of unseen attacks.
Learning Traffic Flow Dynamics with Stochastic Physics-Informed Neural Cellular Automata
A physics-informed neural cellular automaton learns stochastic traffic rules while conserving vehicles and respecting road topology.
An AI-assisted conditioning and geological interpretation workflow for usage in implicit geological modeling
Researchers present an AI toolkit that interprets seismic horizons and faults to speed geological modeling.
Conformal Prediction Sets Quantify Information Gain: A Theoretical Perspective
Paper shows conformal prediction set-size reduction tracks information gain and relates to Shannon mutual information.
Neural Petri flows for chemical reactions
Neural Petri Flow predicts chemical reactions by learning rates while hard-wiring Petri-net conservation rules.
Beyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce Operations
Large-scale tests find Spark MMD reliably detects strong concept drift in a 137.5-million-row table.
EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks
EDiS sparsifies GNN training by caching edge-disjoint subgraphs and recomposing them each epoch under an edge budget.
Technical Report on the Turba Fertilizer Machine Learning Stack in Morocco
Turba’s open-source stack packages reproducible site-specific fertilizer recommendation models for Moroccan cereals.
The Numerical Linear Algebra of Large Language Models
Survey maps numerical linear algebra methods used inside large language models for NLA specialists.
A Hybrid Approach to Malware Detection: Integrating Few-Shot Model-Agnostic Meta-Learning with Autoencoders
A hybrid autoencoder and MAML model detects ransomware from as few as one labeled sample.
SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples
SAGE flags clean-label training poisons from a handful of expert-verified examples using similarity-weighted prediction.
SupraTITO: Transferable Generative Molecular Dynamics for Supramolecular Systems
SupraTITO learns transferable generative molecular dynamics for peptide self-assembly over long physical timescales.
PMosFM: Preconditioned Manifold Matching for One-Step Physics-Constrained Generation
PMosFM learns one-step physics-constrained generation by matching flows on a constraint manifold.
ReCIRC: Rectified Conformal Risk Control
ReCIRC reparameterizes conformal risk control so thresholds target conditional risk while keeping finite-sample marginal guarantees.
A Function-level Dataset of Vulnerable and Fixed Source Code in JavaScript and TypeScript
JsVul pairs vulnerable and fixed JavaScript and TypeScript functions from seven sources.