Survey on AI math foundations, focusing on neural networks.
problem Lack of rigorous mathematical foundation for AI.
method Survey and discussion of theoretical directions in AI.
result Discussion of open problems in AI math.
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
48 results for “theoretical foundations”
Addresses theoretical and practical aspects of Gaussian differential privacy.
problem Theoretical and practical challenges in privacy-preserving data analysis.
method Discussion of f-differential privacy and Gaussian differential privacy.
result Gaussian differential privacy can enhance privacy in various applications.
Logifold improves ensemble machine learning by identifying fuzzy domains.
problem Improving ensemble machine learning accuracy.
method Formulating logifold structure and interpreting local charts of datasets.
result Logifold improves accuracy compared to averaging model outputs.
Mathematical framework for minimum enclosing ball problem.
problem Determining the smallest sphere enclosing a set in d-dimensional space.
method Theoretical framework based on enclosing and partitioning theorems.
result Bounds and relations between circumradius, inradius, diameter, and width.
Disagreement-based approaches generate multiple classifiers and exploit the disagreement among them with unlabeled data to improve learning performance. Co-training is a representative paradigm of them, which trains two classifiers separately on two sufficient and redundant views; while for the applications where there…
CInA method uses attention to improve causal inference.
problem Challenges in causal inference, especially in complex tasks.
method CInA method utilizes self-supervised causal learning with multiple unlabeled datasets and transformer-type architecture.
result CInA effectively generalizes to out-of-distribution datasets and various real-world datasets.
Energy Transformercs.LG
Energy Transformer integrates attention, energy models, and associative memory.
problem Lack of clear theoretical foundations in attention mechanisms and straightforward design of energy functions in energy-based models.
method Proposes Energy Transformer, a sequence of attention layers with a specifically engineered energy function.
result Obtained strong results on graph anomaly detection and classification tasks.
This paper organizes recent deep learning theory advances.
problem Lack of theoretical foundations in deep learning.
method Literature review and categorization into six groups.
result Organized recent advances in deep learning theory.
This paper explains the theoretical inductive bias of Isolation Forest.
problem Lack of theoretical foundation explaining Isolation Forest's success.
method Formulated the growth process of iForest as a random walk, derived expected depth function using transition probabilities.
result Established a theoretical understanding of iForest's effectiveness and parameter adaptability.
The paper explores theories behind graph and relational data vector embeddings.
problem Understanding the foundations of vector embeddings for graphs and relational structures.
method Proposes two theoretical approaches to understand vector embeddings.
result Draws connections between various embedding techniques and suggests future research directions.
Survey on geometric foundations of data reduction methods.
problem High-dimensional data with intrinsic nonlinear structure.
method Spectral manifold learning methods.
result Derivation and convergence analysis of spectral manifold learning.
Distance metric learning is a branch of machine learning that aims to learn distances from the data, which enhances the performance of similarity-based algorithms. This tutorial provides a theoretical background and foundations on this topic and a comprehensive experimental analysis of the most-known algorithms. We sta…
A Group-Theoretic Approach to Computational Abstraction: Symmetry-Driven Hierarchical Clusteringcs.LG
Abstraction plays a key role in concept learning and knowledge discovery; this paper is concerned with computational abstraction. In particular, we study the nature of abstraction through a group-theoretic approach, formalizing it as symmetry-driven---as opposed to data-driven---hierarchical clustering. Thus, the resul…
CoLoRA leverages task similarity to boost fine-tuning efficiency.
problem Efficiently fine-tuning large foundation models with scarce labeled data.
method CoLoRA trains a shared adapter for task similarity and personalized adapters for user-specific tasks.
result CoLoRA significantly boosts fine-tuning performance when tasks are similar.
This paper establishes a theoretical foundation for consistency training in diffusion models.
problem Lack of a comprehensive theoretical understanding of consistency training in diffusion models.
method Demonstrates the necessity of a number of steps in consistency learning exceeding for generating samples within proximity to the target distribution.
result Establishes rigorous insights into the validity and efficacy of consistency models, offering theoretical underpinnings for their utility.
The study initiates a theoretical analysis of dynamic benchmarking models.
problem Lack of theoretical foundation and empirical studies in dynamic benchmarks.
method Examined two realizations of dynamic benchmarking: sequential and hierarchical dependency models.
result Sequential dynamic benchmarks show initial performance improvement but can stall after three rounds due to label noise.
Defines Learning Analytics' foundational structure and scope.
problem Lack of theoretical foundation in Learning Analytics.
method Proposes an axiomatic theory based on psychological learning and LA methodology.
result Clarifies the epistemological stance of Learning Analytics and its limitations.
This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models. It introduces a general condition on composite likelihood decompositions of these models which guarantees the global consistency of distributed estimators, provided the local estimator…
Contrastive learning adapts to data intrinsic dimensions, learning low-dimensional representations.
problem Learning high-dimensional representations from multi-modal data.
method Multi-modal contrastive learning with temperature optimization.
result Contrastive learning adapts to intrinsic dimensions of data, not specified dimensions.
This is an expository article of our work on analogies between knot theory and algebraic number theory. We shall discuss foundational analogies between knots and primes, 3-manifolds and number rings mainly from the group-theoretic point of view.
TDL uses topological features for deep learning models, promising new insights and solutions.
problem Lack of comprehensive theoretical foundations and practical benefits in TDL.
method Discussing open problems and potential solutions in TDL.
result TDL can complement existing graph and geometric learning methods.
Survey interprets foundation models' inner workings.
problem Limited explainability of black-box FMs.
method Interpretable methods to reveal FMs' mechanisms.
result Identifies next research directions for FMs.
Theoretical analysis of t-SNE for visualizing clustered data.
problem Understanding t-SNE for visualizing high-dimensional clustered data.
method Gradient descent approach and power iterations based on graph Laplacian.
result Asymptotic equivalence and limiting behavior of t-SNE's early exaggeration stage.
This thesis explores robust machine learning against adversarial examples.
problem How to create machine learning systems robust to adversarial examples.
method Theoretical exploration and development of new learning algorithms with robustness guarantees.
result Developed new learning algorithms with provable robustness guarantees.
Paper defines XAI concepts using category theory.
problem Lack of precise mathematical definitions for XAI.
method Uses Category theory to define XAI concepts rigorously.
result Establishes a theoretical foundation for XAI.
VALC provides concept-level interpretations of FLMs, overcoming word-level limitations.
problem Lack of higher-level structure interpretation in FLMs' attention weights.
method Formal definition of conceptual interpretation, variational Bayesian framework (VALC).
result VALC finds optimal language concepts for FLM predictions, providing concept-level interpretations.
Survey of theoretical foundations for policy optimization in control.
problem Understanding the theoretical properties of gradient-based methods in control and reinforcement learning.
method Interdisciplinary review of optimization landscape, convergence, and sample complexity for various control problems.
result Recent theoretical results on stability and robustness in learning-based control.
A hybrid impurity measure balances theoretical soundness and computational efficiency.
problem Developing a robust impurity measure for decision trees.
method Integrates Tsallis entropy with an exponential polarization component.
result Simple parametric measures outperform ITC, but ITC variants are competitive with strong theoretical guarantees.
This work formalizes guidance in diffusion models and introduces a stochastic control framework.
problem Lack of a solid theoretical foundation for guidance scheduling in diffusion models.
method Introduces a stochastic optimal control framework to cast guidance scheduling as an adaptive optimization problem.
result Establishes a principled foundation for more effective guidance in diffusion models.
Wide networks learn from adversarial perturbations effectively.
problem Understanding why adversarial examples deceive classifiers and transfer between models.
method Assumed wide two-layer networks, proved with theoretical analysis.
result Adversarial perturbations contain class-specific features for networks to generalize.
SGNs use Hamiltonian mechanics for invertible deep generative modeling.
problem Efficient and exact likelihood evaluation for deep generative models.
method Symplectic structure in latent space, Hamiltonian dynamics for data generation.
result Exact likelihood evaluation without Jacobian calculations.
The paper establishes theoretical foundations for low-rank knowledge distillation in LLMs.
problem Understanding the theoretical underpinnings of low-rank knowledge distillation in LLMs.
method Theoretical framework for low-rank knowledge distillation, including convergence rates and generalization bounds.
result Theoretical analysis reveals optimal rank for minimizing generalization error.
The paper explores neural scaling laws for deep operator networks, offering a theoretical foundation.
problem Understanding neural scaling laws in deep operator networks.
method Theoretical analysis of approximation and generalization errors.
result Established a theoretical framework to quantify neural scaling laws for deep operator networks.
Unified probabilistic foundation for fuzzy simplicial sets in dimensionality reduction.
problem Lack of clear probabilistic interpretation in fuzzy simplicial sets.
method Introducing a probabilistic framework explaining fuzzy simplicial sets as marginals of probability measures on simplicial sets.
result Unified probabilistic theoretical foundation for fuzzy simplicial sets.
This paper provides theoretical foundations for using quantized actions in behavior cloning.
problem Applying autoregressive models to continuous control requires discretizing actions through quantization, which is poorly understood.
method The paper analyzes quantization error propagation and statistical sample complexity, and proposes model-based augmentation.
result Behavior cloning with quantized actions achieves optimal sample complexity, matching existing lower bounds.
ProbFM provides principled uncertainty quantification for financial forecasting.
problem Lack of principled uncertainty quantification in financial applications.
method Probabilistic Time Series Foundation Model with Uncertainty Decomposition using Deep Evidential Regression (DER).
result DER maintains competitive forecasting accuracy while providing explicit epistemic-aleatoric uncertainty decomposition.
Extends field theory foundations to infinitesimal spaces, simplifying complex concepts.
problem Develop rigorous foundations for field theory, especially for infinitesimal spaces.
method Formulates local Lagrangian field theory in a new category of thickened smooth sets.
result Establishes a firm foundation for field theory, including tangent bundles and perturbative considerations.
Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adaptersstat.ML
Paper analyzes asymmetry in LoRA initialization for foundation models.
problem Asymmetry in LoRA initialization affects generalization of foundation models.
method Theoretical analysis of asymmetric LoRA with frozen random factors.
result Upper bound on sample complexity of $ ilde{\mathcal{O}}\left(\frac{\sqrt{r}}{\sqrt{N}}
ight)$ with high probability.
Paper proposes a probabilistic alignment method for domain adaptation.
problem Latent distribution mismatch and miscalibrated uncertainty in adapting large-scale models.
method Bayesian latent transport framework with PAC-Bayesian regularization.
result Reduction in latent manifold discrepancy and improved uncertainty calibration.
OSGM uses online learning to adapt stepsize for faster convergence.
problem Improving convergence rates of first-order methods.
method OSGM combines online learning and feedback functions to adjust stepsize.
result OSGM achieves convergence rates asymptotically no worse than optimal.
This paper establishes a theoretical foundation for super-models via domain adaptation.
problem Reducing computational and data costs in AI for small and medium-sized enterprises.
method Two-stage diffusion process modeling, including pre-training and fine-tuning stages, using the Uhlenbeck-Ornstein process.
result The generalization error of the fine-tuning stage is dominant in domain adaptation.
In this paper, we consider the interpretability of the foundational Laplacian-based semi-supervised learning approaches on graphs. We introduce a novel flow-based learning framework that subsumes the foundational approaches and additionally provides a detailed, transparent, and easily understood expression of the learn…
We study the task of online boosting--combining online weak learners into an online strong learner. While batch boosting has a sound theoretical foundation, online boosting deserves more study from the theoretical perspective. In this paper, we carefully compare the differences between online and batch boosting, and pr…
The study provides theoretical foundations for using smaller instances to predict algorithm performance on larger ones.
problem Scalability challenge in evaluating algorithms on large instances.
method Formalized size generalization, providing theoretical guarantees for predicting algorithm performance on large instances using smaller, representative instances.
result Characterized the subsample size sufficient to ensure performance on the subsample reflects performance on the full instance.
Approximate inference algorithm is one of the fundamental research fields in machine learning. The two dominant theoretical inference frameworks in machine learning are variational inference (VI) and Markov chain Monte Carlo (MCMC). However, because of the fundamental limitation in the theory, it is very challenging to…
Research reveals deep networks often learn low-rank structures, leading to more efficient training and fine-tuning.
problem Efficient training and deployment of large-scale deep learning models.
method Complementary theoretical perspectives on low-rank structures during training and convergence, and practical applications of LoRA and masked training.
result Understanding and exploiting low-rank structures can improve efficiency and effectiveness of training and fine-tuning.
Unified framework connects credit risk metrics with information theory.
problem Disconnection between industry-standard metrics and statistical theory.
method Unified information-theoretic framework, proving IV equals PSI, deriving standard errors, formalizing trade-off, automated binning with XGBoost.
result Unified framework connects IV and PSI, providing statistical foundation for metrics.
Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Directionstat.ML
This paper reviews information theory in open-world machine learning.
problem Lack of a unified theoretical foundation for open-world machine learning.
method Synthesis of information theoretic approaches.
result Established a pathway toward provable and trustworthy open world intelligence.