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.

168,695 papers · 148 categories

Trend · papers per month

160320479639 · Jun 202019922001200920172026
48 results for Decision Boundary Complexity

This work connects the Hessian to the decision boundary complexity in neural networks.

problem Understanding the decision boundary complexity in high-dimensional input space.
method Characterizing the decision boundary using the Hessian top eigenvectors and analyzing the number of outliers.
result The number of outliers in the Hessian spectrum is proportional to the complexity of the decision boundary.

New method measures generalizability of deep neural networks based on decision boundary complexity.

problem Lack of generalization methods for deep neural networks.
method Created Decision Boundary Complexity (DBC) score to measure DNN complexity.
result Simpler decision boundaries lead to better generalizability, supporting Occam's Razor.

Measures neural network decision boundary volume to predict model performance.

problem Understanding the geometry of deep learning models for better performance.
method Local surface volumes to measure decision boundary, applying Weyl's tube formula.
result Smaller surface volume correlates with higher classification accuracy.

Local decision boundary approximation improves model explanations for complex models.

problem Challenges in explaining complex, opaque machine learning models.
method Train a variational autoencoder to learn a latent space and map it to meaningful attributes. Use these attributes to approximate the local decision boundary and explain model predictions.
result Can recover latent attributes that determine class decisions in a new benchmark data set.

Transformers fine-tuned on synthetic data boost tabular data classification performance.

problem Improving tabular data classification accuracy.
method Fine-tuning ICL-transformers on synthetic datasets with complex decision boundaries.
result Fine-tuned ICL-transformers outperform regular neural networks on real-world datasets.

SBAMDT uses adaptive soft splits to model complex decision boundaries.

problem Limited ability of standard decision trees to capture complex decision boundaries.
method Probabilistic additive decision tree model with adaptive soft multivariate splits.
result Demonstrated improved predictive performance on synthetic and real datasets.

Maxout networks show similar complexity issues as ReLU networks.

problem Understanding the complexity of maxout networks and decision boundaries.
method Analyzing the parameter space and decision boundaries, obtaining lower bounds, and investigating initialization procedures.
result Maxout networks exhibit a wide range of complexity, similar to ReLU networks.

New method reduces model bias and variance by adjusting training sample weights based on label uncertainty.

problem Tradeoff between model bias and variance in classification models.
method Estimate label uncertainty, adjust training sample weights, and fine-tune decision boundary.
result Improves model performance and reduces variance in physical activity recognition.

New method counts boundary pieces in ReLU classifiers for better complexity measure.

problem Current classification complexity measures are misleading and ineffective.
method Developed a novel method using tropical geometry to count exact boundary pieces.
result Boundary piece count is negatively correlated with robustness.

Deep learning models have been the subject of study from various perspectives, for example, their training process, interpretation, generalization error, robustness to adversarial attacks, etc. A trained model is defined by its decision boundaries, and therefore, many of the studies about deep learning models speculate…

2019-08-07abs ↗pdf ↗

Study decision boundaries using heat diffusion and probabilistic techniques.

problem Understanding the geometry of decision boundaries in machine learning.
method Using Brownian motion and probabilistic techniques to analyze decision boundaries.
result Decision boundaries exhibit persistent 'wiggly and fuzzy' regions, even under adversarial attacks.

Deep neural networks and in particular, deep neural classifiers have become an integral part of many modern applications. Despite their practical success, we still have limited knowledge of how they work and the demand for such an understanding is evergrowing. In this regard, one crucial aspect of deep neural network c…

2019-12-24abs ↗pdf ↗

The paper shows how neural networks with less decision boundary variability generalize better.

problem Improving neural network generalizability by reducing decision boundary variability.
method Introduces new measures (algorithm DB variability and (ε,η)(ε, η)-data DB variability) to quantify decision boundary variability and proves theoretical bounds on generalizability.
result Neural networks with lower decision boundary variability have better generalizability, as shown by extensive experiments and theoretical bounds.

Deep learning models generalize by extending decision boundaries outside the convex hull of training data.

problem Understanding how deep learning models generalize beyond their training data.
method Investigation of decision boundaries inside and outside the convex hull of training sets, using various neural network architectures and training regimes.
result Over-parameterization is necessary for deep learning models to extend decision boundaries outside the convex hull of their training data.

Deep networks can overfit benignly but still be vulnerable to adversarial attacks.

problem Adversarial vulnerability of deep neural networks trained with benign overfitting.
method Investigated causes of adversarial vulnerability, identified label noise as a key factor, and explored the impact of training procedures and representation learning.
result Adversarial robustness requires more complex decision boundaries than simple ones, suggesting the need for better representation learning.

The goal of this paper is to analyze the geometric properties of deep neural network classifiers in the input space. We specifically study the topology of classification regions created by deep networks, as well as their associated decision boundary. Through a systematic empirical investigation, we show that state-of-t…

2017-05-26abs ↗pdf ↗

Proposes a method to speed up model selection for classification.

problem Time-consuming model selection process and lack of dataset-specific insights.
method Relaxes decision boundaries of neural decision trees to find equivalent or better models.
result Reduces the scope of exploration needed for model selection.

Recognition of Seifert fibered spaces with boundary is computationally tractable.

problem Recognizing Seifert fibered spaces with boundary.
method Proving the existence of fundamental horizontal surfaces and normal vertical annuli with bounded total weight.
result The decision problem is in NP and the construction problem is in FNP.

Paper proposes a new classifier for hyperbolic spaces using horospherical boundaries.

problem Optimization of large margin classifiers in hyperbolic spaces.
method Horospherical decision boundaries for geodesically convex optimization.
result Geodesically convex optimization leads to globally optimal solutions.

Decision trees and shallow neural networks have different geometric complexities, impacting their interpretability and accuracy.

problem The geometric simplicity of decision boundaries in decision trees conflicts with the approximation capabilities of shallow neural networks.
method Analysis of the Radon total variation (RTV) seminorm to compare geometric complexity of decision regions and neural network approximations.
result Smooth barrier scores can approximate decision regions with finite RTV, but their performance depends on the tube-mass condition near the decision boundary.

Decision trees are a popular technique in statistical data classification. They recursively partition the feature space into disjoint sub-regions until each sub-region becomes homogeneous with respect to a particular class. The basic Classification and Regression Tree (CART) algorithm partitions the feature space using…

2015-04-14abs ↗pdf ↗

Enhanced ODT with Feature Concatenation boosts learning efficiency.

problem Insufficient learning efficiency of ODT due to linear projections not being transmitted to child nodes.
method Feature Concatenation ( exttt{FC-ODT}) to transmit linear projections along decision paths.
result Experiments show exttt{FC-ODT} outperforms state-of-the-art decision trees with a limited tree depth.

Study robustness of polynomial neural networks using algebraic geometry.

problem Certify robustness radius of polynomial neural networks.
method Metric algebraic geometry, Euclidean distance degree, symbolic elimination, homotopy-continuation methods.
result Found decision boundaries with lower ED degree than generic cubic hypersurfaces.

Paper extends transfer learning for decision rules, improving treatment rule estimation.

problem Estimating optimal individualized treatment rules under changing conditions.
method Bayes decision rules and low-dimensional empirical risk minimization.
result Consistent estimators and risk bounds established under mild conditions.

The goal of a decision-based adversarial attack on a trained model is to generate adversarial examples based solely on observing output labels returned by the targeted model. We develop HopSkipJumpAttack, a family of algorithms based on a novel estimate of the gradient direction using binary information at the decision…

2019-04-03abs ↗pdf ↗

Local surrogate models, to approximate the local decision boundary of a black-box classifier, constitute one approach to generate explanations for the rationale behind an individual prediction made by the back-box. This paper highlights the importance of defining the right locality, the neighborhood on which a local su…

2018-06-19abs ↗pdf ↗

A set of introductory notes on the subject of data classification using a linear classifier and least-squares cost function, and the negative effect of the presence of outliers on the decision boundary of the linear discriminant. We also show how a simple scaling could make the outlier less significant, thereby obtaini…

2018-08-28abs ↗pdf ↗

Deep neural networks achieve optimal learning rates for high-dimensional classification.

problem Learning classification functions from noisy data with smooth boundaries.
method Empirical risk minimization over deep neural networks for locally Barron-regular decision boundaries.
result Optimal estimation rates are independent of dimension and can be achieved by deep neural networks.

Develops MGQDA for multi-group classification with theoretical guarantees and practical applications.

problem Complex multi-group classification problems with nonlinear decision boundaries and group-specific covariance patterns.
method MGQDA, a method based on quadratic discriminant analysis that projects predictors onto a lower-dimensional subspace.
result MGQDA achieves competitive or improved predictive performance compared to existing methods.

Unified framework improves cross-corpus EEG emotion recognition by aligning prototypes and refining decision boundaries.

problem Cross-corpus EEG emotion recognition suffers from performance degradation due to physiological variability and device inconsistencies.
method Prototype-driven Adversarial Alignment (PAA) framework with three configurations: local, contrastive, and boundary-aware.
result State-of-the-art performance improvements across four cross-corpus evaluation protocols.

In practical work with American put options, it is important to be able to know when to exercise the option, and when not to do so. In computer simulation based on the standard theory of geometric Brownian motion for simulating stock price movements, this problem is fairly easy to handle for options with a short lifesp…

2004-12-16abs ↗pdf ↗

Paper introduces CoD for few-shot task-aware knowledge distillation using counterfactual explanations.

problem Lack of data for task-aware distillation in resource-constrained scenarios.
method Counterfactual-explanation-infused Distillation CoD for few-shot task-aware knowledge distillation.
result CoD achieves superior performance with significantly fewer samples than baseline methods.