Research
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

58116173231 · Jun 202019922001200920172026
48 results for knowledge injection

Hybrid framework injects TSLM insights into GRLM for robust time-series reasoning.

problem Lack of domain-specific knowledge in large language models for time-series reasoning.
method Hybrid knowledge-injection framework combining RLVR for efficient knowledge transfer.
result Consistently outperforms existing models by 7.9%-26.1% on multivariate time-series benchmarks.

Proposes a method for neural networks to learn causal relationships and humans to contest and modify them.

problem Neural networks learn relevant causal relationships unclearly and are black-box, making them hard to debug.
method Two-way interaction between neural networks and humans, allowing contestation and modification of causal graphs.
result Improves predictive performance up to 2.4x and produces smaller networks up to 7x compared to SOTA.

New algorithm improves interpretability in sequence classification.

problem Lack of human-independent interpretability metrics in sequence classification.
method Combines linear classifiers with background knowledge embeddings to create a new feature space.
result Preserves predictive power while delivering more interpretable models.

Arguments in favor of injecting symbolic knowledge into neural architectures abound. When done right, constraining a sub-symbolic model can substantially improve its performance and sample complexity and prevent it from predicting invalid configurations. Focusing on deep probabilistic (logical) graphical models -- i.e.…

2019-12-19abs ↗pdf ↗

Noise injection improves inference privacy in DNN models.

problem Malicious servers can infer sensitive attributes from input data.
method Adaptive Noise Injection (ANI) using a lightweight DNN on the client.
result Significant improvement in privacy (up to 48.5% degradation in sensitive-task accuracy with <1% degradation in primary accuracy).

The paper studies ray transforms on surfaces with negative curvature, proving injectivity and determining connections and Higgs fields.

problem Injectivity of ray transforms on surfaces with negative curvature and determination of connections and Higgs fields.
method Analysis of Gaussian thermostats on compact Riemannian surfaces with negative curvature, proving injectivity and determining connections and Higgs fields.
result Injectivity of the thermostat ray transform and determination of connections and Higgs fields.

For a compact Riemannian manifold with boundary, endowed with a magnetic potential αα, we consider the problem of restoring the metric gg and the magnetic potential αα from the values of the Mañé action potential between boundary points and the associated linearized problem. We study simple magnetic systems. In this…

2006-11-25abs ↗pdf ↗

Domain knowledge helps detect adversarial examples in multi-label classification.

problem Detecting adversarial examples in multi-label classification.
method Convert domain knowledge into constraints and inject them into a semi-supervised learning problem.
result Domain-knowledge constraints help detect adversarial examples effectively.

Optimal dividend strategy with ratcheting and capital injection under Cramér-Lundberg model.

problem Optimal dividend payout for an insurance company with ratcheting constraints and capital injections.
method Systematic probabilistic and PDE-based approach to solve HJB equation, constructing strong solution and optimal strategy.
result Existence and uniqueness of strong solution, explicit optimal feedback control strategy.

Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is used to train a more compact student model with better inference efficiency. Throug…

2020-02-10abs ↗pdf ↗

This paper improves attacks on recommender systems by solving optimization problems more precisely.

problem Adversarial injection attacks on recommender systems.
method Solving optimization problems for generating fake user interactions more accurately.
result The exact solution for generating fake users leads to a much larger impact on recommender systems.

OMIC improves matrix completion with orthonormal side information and nuclear-norm regularization.

problem Matrix completion with improved interpretability and adaptability.
method OMIC combines orthonormal side information and nuclear-norm regularization, optimized by a converging algorithm.
result OMIC outperforms state-of-the-art methods in synthetic and real-world datasets.

We propose a feed-forward inference method applicable to belief and neural networks. In a belief network, the method estimates an approximate factorized posterior of all hidden units given the input. In neural networks the method propagates uncertainty of the input through all the layers. In neural networks with inject…

2018-03-28abs ↗pdf ↗

Injectivity of ReLU networks is characterized for generative models and inverse problems.

problem Injectivity in ReLU networks for generative models and inverse problems.
method Layerwise analysis, worst-case Lipschitz constants, differential topology, random projections.
result Global injectivity of ReLU networks requires expansivity between 3.4 and 10.5 for Gaussian matrices.

Improved physics-integrated generative models with noise robustness and fidelity.

problem Enhancing generative models to produce outputs that comply with physical laws and improve generalization.
method Integrating variational autoencoder with planar normalizing flow and attention mechanisms to learn latent posterior distributions and mitigate noise.
result Significant improvement in reconstruction quality and robustness against noise.

PS-KD distills a model's own knowledge to soften hard targets during training.

problem Improving generalization of deep neural networks by softening hard targets.
method Progressive self-knowledge distillation (PS-KD) that progressively distills a model's own knowledge to soften hard targets.
result PS-KD improves accuracy and provides high quality of confidence estimates in terms of calibration and ordinal ranking.

The paper analyzes optimal dividend and capital injection strategies under time-inconsistent preferences.

problem Optimal dividend and capital injection strategies under time-inconsistent preferences.
method Diffusion risk model with general discount functions, weak equilibrium definition, HJB equation system.
result Explicit solutions and threshold types of optimal strategies derived under different discount functions.

A quasi-geodesic is Morse if and only if it is strongly contracting in injective spaces.

problem Characterizing Morse quasi-geodesics in injective spaces.
method Proving equivalence between Morse and strongly contracting quasi-geodesics.
result Injective metric spaces have the Morse local-to-global property and acylindrically hyperbolic groups with Morse elements.

This paper connects noise injection to Bayesian inference for neural networks, improving model uncertainty.

problem Improving the reliability and confidence of neural network predictions through uncertainty quantification.
method Introducing noise into neural network parameters during training and inference to estimate prediction uncertainty.
result The MCNI method outperforms baseline models in regression and classification tasks.

Lecture notes on group actions on injective spaces and Helly graphs.

problem Understanding group actions on specific metric spaces.
method Review of injective metric spaces and Helly graphs, elementary properties, constructions, and exercises.
result Presentation of various constructions of injective metric spaces and Helly graphs with interesting group actions.

Reservoir subspace injection improves online ICA by preserving injected features.

problem Discarding injected features in top-nn whitening can degrade performance.
method Formalized reservoir subspace injection (RSI) and developed diagnostics (IER, SSO, ρ_x) to identify and mitigate the failure mode.
result RSI controller preserves passthrough retention, improving performance by up to 2.2 dB.

Injective and surjective neural operators for function spaces.

problem Tackles injective and surjective neural operators in function spaces.
method Combines prior work in ReLU and operator learning, uses Fredholm theory and Leray-Schauder degree theory.
result Injective and surjective neural operators are universal approximators and maintain their properties in finite-rank implementations.

Smooths metrics on manifolds with curvature bounds and injectivity radius constraints.

problem Smooth metrics on manifolds with curvature and injectivity constraints.
method Bi-Lipschitz smoothing with controlled smoothing and volume lower bounds.
result Proves existence of smooth metrics with curvature bounds and injectivity radius constraints.

Nonuniform tubular neighborhoods of curves in Euclidean n-space are studied by using weighted distance functions and generalizing the normal exponential map. Different notions of injectivity radii are introduced to investigate singular but injective exponential maps. A generalization of the thickness formula is obtaine…

2007-05-16abs ↗pdf ↗

In this paper, we obtain two-sided bounds for the volumes of the Aloff-Wallach spaces W(p,q),W(p,q), compute maximal and minimal sectional curvature for the spaces W(n,n+1),W(n,n+1), and use this information to estimate the injectivity radii: We derive an upper bound for the injectivity radii of W(p,q)W(p,q) and a lower bound for the …

2005-11-24abs ↗pdf ↗

Researchers develop method to protect against 'weight poisoning' attacks on pre-trained models.

problem The security threat of downloading untrusted pre-trained weights that can be manipulated after fine-tuning.
method RIPPLe regularization method and Embedding Surgery initialization procedure.
result Demonstrated that weight poisoning attacks are possible even with limited knowledge of the dataset and fine-tuning procedure.

Injectivity of geodesic ray transform on specific Finsler manifolds proven.

problem Injectivity of geodesic ray transform on spherically symmetric reversible Finsler manifolds.
method Reduction to invertibility of generalized Abel transforms using angular Fourier series and Taylor expansions of geodesics.
result Injectivity of geodesic ray transform proven on specified Finsler manifolds.

The thesis introduces methods to use semantic hierarchy in image classification.

problem Limited work in training image classifiers with non-conventional external guidance.
method Injects label hierarchy knowledge into arbitrary classifiers and uses order-preserving embeddings for image classification.
result Both embedding-based models and CNN-classifiers with hierarchical information outperform a hierarchy-agnostic model.