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.

169,291 papers · 148 categories

Trend · papers per month

90180270360 · Jun 202019922001200920182026
48 results for learnable representations

The paper shows how to avoid the trivial representation in IB by choosing the right β.

problem Lack of theoretical guidance for choosing β in the IB method.
method Identifying a phase transition between learnable and unlearnable representations based on β.
result IB-Learnability is defined by the largest confident, typical, and imbalanced subset of examples.

Unified theory for representation learning using learnable functions.

problem Insufficient theoretical understanding of unsupervised and self-supervised learning.
method Discriminative theoretical framework for analyzing sample complexity.
result Learnable regularization functions can reduce the amount of labeled data needed.

Paper proposes learnable topological features for efficient phylogenetic inference.

problem Finding appropriate topological structures for phylogenetic inference tasks requires significant design effort and domain expertise.
method Combines raw node features with graph neural networks to automatically adapt to different tasks.
result Demonstrates effectiveness and efficiency on simulated and real data phylogenetic inference tasks.

End-to-end learnable network for safer self-driving with interpretable intermediate representations.

problem Safe motion planning for self-driving vehicles.
method Differentiable semantic occupancy representation for cost calculation in motion planning.
result Significantly outperforms state-of-the-art planners in imitating human behaviors and producing safer trajectories.

This paper extends financial theory to measure learnable market structure under computational constraints.

problem Understanding learnable market structure under bounded computational capacity.
method Introduces financial epiplexity as a measure of learnable market structure, extending classical information theory.
result Proves that equal entropy does not imply equal epiplexity and derives thresholds for useful regimes.

MoleculeNet benchmarks molecular machine learning algorithms.

problem Lack of a standard benchmark for molecular machine learning.
method Curated multiple public datasets, established evaluation metrics, released open-source implementations.
result Learnable representations offer the best performance in molecular machine learning.

A new autoencoder combines deep learning with SVD to reduce model complexity.

problem Overcoming the Kolmogorov barrier in high-dimensional systems.
method Learnable weighted hybrid autoencoder combining SVD and deep learning.
result Empirically, the model exhibits a sharpness thousands of times smaller than other models.

Study on learnability of Schatten--von Neumann operators in learning theory.

problem Learnability of Schatten--von Neumann operators in infinite-dimensional settings.
method Adapted representer theorem to convert infinite-dimensional optimization to convex finite-dimensional problem.
result Schatten--von Neumann operators are probably approximately correct (PAC)-learnable via practical convex program for any p<p < \infty.

Deep networks struggle to learn efficient representations of simple functions.

problem Can deep learning methods find efficient representations of simple functions?
method Trained deep neural networks on the parity function and fast Fourier transform, using gradient-based optimization.
result Deep networks require initialization close to exact solutions to learn efficient representations of simple functions.

A hierarchy of GNNs based on learnable local features is proposed.

problem Limited understanding of GNN architectures and their systematic construction.
method A hierarchy of GNNs based on aggregation regions is derived, and theoretical results are provided.
result Simple GNN architecture exceeds Weisfeiler-Lehman graph isomorphism test.

Study extends learnability equivalence to multi-class and regression, overcoming binary classification limits.

problem Equivalence of online and private learnability in multi-class and regression settings.
method Introduced a novel Littlestone dimension variant and threshold functions for multi-class classification.
result Online learnability implies private learnability in multi-class classification but not in regression.

New interpretation of RNN forget gate improves learnability for long-term sequential data.

problem Improving learnability of recurrent neural networks for long-term temporal dependencies.
method Generalized theory of gated RNNs, focusing on gradient behavior over time.
result Existing RNNs satisfy the gradient condition for initial training, suggesting validity of forget gate interpretation.

Example shows learnable distributions not privately learnable.

problem Learnable distributions under non-private conditions not transferable to differential privacy.
method Example of a distribution class learnable up to constant error in total variation distance but not under differential privacy.
result Contradicts conjecture of Ashtiani on learnability under differential privacy.

TACOMA improves cancer biomarker validation by incorporating deep features.

problem Improving accuracy and repeatability in TMA image scoring.
method Incorporating deep learning representations learned through unsupervised clustering and recursive space partitioning.
result Reduced error rate by about 6% on breast cancer TMA images.

No single parameter characterizes the learnability of probability distributions.

problem Finding a parameter to characterize the learnability of probability distributions.
method Analyzing various notions of learnability and showing impossibility results.
result No such parameter exists for characterizing learnability of probability distributions.

We consider the fundamental question of learnability of a hypotheses class in the supervised learning setting and in the general learning setting introduced by Vladimir Vapnik. We survey classic results characterizing learnability in term of suitable notions of complexity, as well as more recent results that establish …

2013-03-24abs ↗pdf ↗

New insights into Valiant's learnability model reveal classes learnable with membership queries.

problem Which classes are learnable in Valiant's original model?
method Characterization using poly-size adaptive query-compression schemes and techniques for arbitrary domains.
result Learnability in Valiant's model is sandwiched between PAC and query-less variants, with halfspaces learnable with queries.

Transformers tend to learn more symmetric functions in sequence data.

problem Understanding inductive bias in Transformers with infinitely over-parameterized models.
method Analyzing Transformers in the Gaussian process limit, using representation theory of the symmetric group.
result Transformers are biased towards more permutation symmetric functions, and this can be quantitatively predicted.

New approach to nonuniform learnability using measure theory.

problem Nonuniform learnability of hypotheses with varying sample sizes.
method Measure theoretic approach to redefine nonuniform learnability, introducing a new algorithm (Generalize Measure Learnability).
result Achieved statistical consistency in learning countable hypothesis classes.

The study analyzes neural network predictions of knot invariants and finds that braid representations work best.

problem Understanding and predicting knot invariants using neural networks.
method Investigated different knot representations and invariants, proposed a cosine similarity score.
result Braid representations are best for predicting knot invariants, and some invariants are easier to learn than others.

New algorithm learns regression models privately under growth condition.

problem Private learning of nonparametric regression models.
method Novel filtering procedure to output stable hypotheses for nonparametric function classes.
result Established first nonparametric private learnability guarantee for diverging fat shattering dimensions.

Deep models learn to parse complex language structures from local data patterns.

problem Understanding how deep models parse and represent language structures.
method Introduced tunable probabilistic context-free grammars and a learning algorithm inspired by deep networks.
result Data correlations across scales enable hierarchical language representations.

UNIPoint universally approximates point process intensities.

problem How to precisely describe the flexibility of point process models.
method Proof using Stone-Weierstrass Theorem, transfer functions, and recurrent neural networks.
result UNIPoint performs better than other models on synthetic and real-world datasets.

Adding supplementary axes improves neural network learnability and accuracy.

problem Overfitting and computational cost in deep neural networks.
method Analysis of a simple MLP model and comparison with and without supplementary information.
result Neural networks with supplementary axes show more robust and accurate training results.

In this paper we study the approximate learnability of valuations commonly used throughout economics and game theory for the quantitative encoding of agent preferences. We provide upper and lower bounds regarding the learnability of important subclasses of valuation functions that express no-complementarities. Our main…

2011-08-29abs ↗pdf ↗

Characterizes learnability of forgiving 0-1 loss functions in multiclass settings.

problem Understanding when multiclass learning with forgiving 0-1 loss functions is possible.
method Introduces a new combinatorial dimension based on Natarajan Dimension to determine learnability.
result A hypothesis class is learnable if and only if the Generalized Natarajan Dimension is finite.

New findings on depth vs. width in neural networks, showing depth can improve learnability.

problem Understanding the role of depth in neural networks, especially when width is unbounded.
method Analyzing sample complexity for learnability in norm-controlled depth-2 and depth-3 ReLU networks.
result Depth can improve learnability of functions that are otherwise unlearnable with depth-2 networks.

The paper solves open questions in computable PAC learning, providing a complete landscape.

problem Understanding the boundaries and capabilities of computable PAC learning.
method Analyzing and constructing decidable hypothesis classes with different sample complexities and Littlestone dimensions.
result A complete understanding of CPAC learnability, answering open questions and confirming conjectures.

System discovers new classes from unlabeled data, improving model performance.

problem Handling datapoints outside initial training distribution.
method Develops new classes through semi-supervised learning, using Dataset Reconstruction Accuracy and class learnability.
result Demonstrates improved model quality through automatic class discovery.

This work proves DP learnability implies online learnability for general classification tasks.

problem Link between differential privacy and online learning for general classification tasks.
method Establishes Ramsey-type theorems for trees to prove DP learnability implies online learnability.
result DP learnability implies online learnability for general classification tasks.

A new KAN variant uses sinusoidal activations to approximate functions.

problem Approximating multivariable functions using neural networks.
method Replacing inner and outer functions in Kolmogorov-Arnold representation with weighted sinusoidal functions.
result The new KAN variant outperforms fixed-frequency Fourier transform and achieves comparable performance to MLPs.

Study robust regression learning under adversarial attacks.

problem Understanding which function classes are learnable in the presence of adversarial attacks.
method Introduced a novel agnostic sample compression scheme and used fat-shattering dimension to construct adversarially robust sample compression schemes.
result Finite fat-shattering dimension classes are learnable in both realizable and agnostic settings.