A new reward learning module improves imitation learning in high-dimensional environments.
problem Challenges in high-dimensional environments for imitation learning.
method Generative model to generate intrinsic reward signals.
result Our method outperforms state-of-the-art IRL methods on Atari games.
In this study, we prove that an intrinsic low dimensionality of covariates is the main factor that determines the performance of deep neural networks (DNNs). DNNs generally provide outstanding empirical performance. Hence, numerous studies have actively investigated the theoretical properties of DNNs to understand thei…
A new multi-objective RL framework improves intrinsic exploration performance.
problem Sub-optimal exploration performance due to ad-hoc handling of intrinsic exploration.
method A multi-objective RL framework where both exploration and exploitation are optimized as separate objectives.
result EMU-Q method outperforms classic and other intrinsic RL methods on benchmarks.
In many sequential decision making tasks, it is challenging to design reward functions that help an RL agent efficiently learn behavior that is considered good by the agent designer. A number of different formulations of the reward-design problem, or close variants thereof, have been proposed in the literature. In this…
Study provides bounds for estimating intrinsic dimension using Gaussian kernels.
problem Estimating intrinsic dimension from data.
method Finite-sample concentration and anti-concentration bounds for Gaussian kernel sums.
result Explicit dependence on sample size, bandwidth, and geometric parameters.
We propose a new method for estimating the intrinsic dimension of a dataset by applying the principle of regularized maximum likelihood to the distances between close neighbors. We propose a regularization scheme which is motivated by divergence minimization principles. We derive the estimator by a Poisson process appr…
Modern large-scale datasets are frequently said to be high-dimensional. However, their data point clouds frequently possess structures, significantly decreasing their intrinsic dimensionality (ID) due to the presence of clusters, points being located close to low-dimensional varieties or fine-grained lumping. We test a…
The existing approaches to intrinsic dimension estimation usually are not reliable when the data are nonlinearly embedded in the high dimensional space. In this work, we show that the explicit accounting to geometric properties of unknown support leads to the polynomial correction to the standard maximum likelihood est…
Efficient method estimates intrinsic dimension for big data.
problem Estimating intrinsic dimension for large datasets is costly and complex.
method Proposes a matrix-vector product-based approach for efficient intrinsic dimension estimation.
result Demonstrates superior performance compared to state-of-the-art methods.
New RL approach uses future state and action visitation measures for better exploration.
problem Improving exploration in reinforcement learning.
method Intrinsic reward based on future state and action visitation measures, using contraction operators.
result Policies achieve good state-action space coverage and high performance.
Study finds intrinsic multifractality in maize and barley spot markets, but not in wheat and rice.
problem Understanding the complex price behavior of global grain spot markets.
method Utilized multifractal fluctuation analysis (MF-DFA) to investigate intrinsic multifractality.
result Intrinsic multifractality found in maize and barley sub-indices, but not in wheat and rice.
Introduces intrinsic Hopf-Lax semigroup linking to intrinsic slope.
problem Understanding intrinsic Hopf-Lax semigroup and its relation to intrinsic slope.
method Introduces and proves the link between intrinsic Hopf-Lax semigroup and intrinsic slope.
result Intrinsic Hopf-Lax semigroup is a subsolution of Hamilton-Jacobi type equality.
Scaling laws found for reinforcement learning performance with model size and compute.
problem Challenges in extending generative modeling scaling laws to reinforcement learning.
method Introduced intrinsic performance as a monotonic function of mean episode return.
result Intrinsic performance scales as a power law in model size and environment interactions.
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.
W2S FT often outperforms weak teachers due to low intrinsic dimensionality.
problem Understanding why weak-to-strong finetuning outperforms weak models.
method Analyzing W2S in ridgeless regression setting, focusing on variance reduction.
result Weak teacher's variance is inherited by strong student in shared feature subspace, reduced in discrepancy subspace.
The paper introduces a new intrinsic reward method for exploration in reinforcement learning.
problem Improving exploration in reinforcement learning agents.
method Intrinsic rewards proportional to the entropy of future state-action features.
result The new objective leads to improved visitation of features within individual trajectories.
The paper refutes the manifold hypothesis for image data and proposes the union of manifolds hypothesis.
problem The manifold hypothesis fails to capture the structure of image data.
method Empirical verification of the union of manifolds hypothesis on image datasets.
result Image data lies on a disconnected set with varying intrinsic dimensions.
The success of modern Artificial Intelligence (AI) technologies depends critically on the ability to learn non-linear functional dependencies from large, high dimensional data sets. Despite recent high-profile successes, empirical evidence indicates that the high predictive performance is often paired with low robustne…
Survey of intrinsically linked or knotted graphs.
problem Understanding graphs that are inherently knotted or linked.
method Survey of existing results.
result Discussion of known properties of intrinsically linked or knotted graphs.
The paper studies properties of intrinsically Lipschitz constants in metric spaces.
problem Investigating properties of intrinsically Lipschitz constants.
method Introduced Leibniz and product formulas for intrinsic slope.
result Formulated Leibniz and product formulas for intrinsic slope.
A method uses ITD and XGBoost for precise power transformer fault diagnosis.
problem Fault diagnosis of power transformers using DGA data.
method Ranking DGA parameters by skewness, extracting ITD features, and using an XGBoost classifier.
result The method achieves over 95% accuracy in classification.
GeLoRA optimizes LoRA fine-tuning by dynamically adjusting ranks based on intrinsic dimensionality.
problem Efficient fine-tuning of large language models with limited computational resources.
method GeLoRA computes intrinsic dimensionality to adaptively select LoRA ranks, balancing expressivity and efficiency.
result GeLoRA consistently outperforms recent baselines within the same parameter budget on multiple tasks.
This study examines Gaussian processes on Riemannian manifolds and proves contraction rates.
problem Comparing intrinsic vs. extrinsic Gaussian processes on Riemannian manifolds.
method Proves optimal contraction rates for intrinsic Matérn Gaussian processes on compact Riemannian manifolds.
result Intrinsic Gaussian processes on Riemannian manifolds achieve better performance than extrinsic ones.
We introduce new sufficient conditions for intrinsic knotting and linking. A graph on n vertices with at least 4n-9 edges is intrinsically linked. A graph on n vertices with at least 5n-14 edges is intrinsically knotted. We also classify graphs that are 0, 1, or 2 edges short of being complete partite graphs with respe…
Paper extends Bayesian Cramér-Rao bound with geometric considerations.
problem Estimation of covariance matrices with geometric structures.
method Intrinsic Bayesian Cramér-Rao bound with Riemannian geometry.
result Performance bounds for covariance matrix estimation.
Neural networks' performance scales with data size, explained by data manifold dimensionality.
problem Understanding the scaling of neural network performance with the number of parameters.
method Explained by the intrinsic dimension of the data manifold, confirmed through teacher/student framework and various datasets.
result The scaling exponent α is approximately 4 divided by the intrinsic dimension d of the data manifold.
New proof shows diffusion models implicitly estimate intrinsic dimensionality.
problem Estimating intrinsic dimensionality of data from diffusion models.
method Formal proof of FLIPD under realistic assumptions.
result FLIPD's correctness proven under realistic conditions.
New graph shows edge deletion/contraction doesn't always result in intrinsically linked graphs.
problem Edge operations in intrinsically knotted graphs don't always produce intrinsically linked graphs.
method Presented a new intrinsically knotted graph.
result Edge operations in intrinsically knotted graphs don't always result in intrinsically linked graphs.
New method estimates intrinsic dimensionality using angles, not distances.
problem Estimating local intrinsic dimensionality accurately.
method Introduces a new estimator using the distribution of angles between neighbor points.
result New estimator behaves similarly but complementarily to existing measures of intrinsic dimensionality.
A directed graph G is intrinsically linked if every embedding of that graph contains a non-split link L, where each component of L is a consistently oriented cycle in G. A tournament is a directed graph where each pair of vertices is connected by exactly one directed edge. We consider intr…
We classify graphs that are 0, 1, or 2 edges short of being complete partite graphs with respect to intrinsic linking and intrinsic knotting. In addition, we classify intrinsic knotting of graphs on 8 vertices. For graphs in these families, we verify a conjecture presented in Adams' "The Knot Book": If a vertex is remo…
Graph Ricci flow reveals hidden hierarchies in stock market correlations.
problem Detecting hidden structures in the complex stock market graph.
method Using graph Ricci curvature and flow techniques to analyze the NASDAQ 100 index.
result Algorithm detects hidden hierarchies, community behavior, and clustering in financial markets.
In the last decades the estimation of the intrinsic dimensionality of a dataset has gained considerable importance. Despite the great deal of research work devoted to this task, most of the proposed solutions prove to be unreliable when the intrinsic dimensionality of the input dataset is high and the manifold where th…
The focus of this paper is on intrinsic methods to detect overfitting. By intrinsic methods, we mean methods that rely only on the model and the training data, as opposed to traditional methods (we call them extrinsic methods) that rely on performance on a test set or on bounds from model complexity. We propose a famil…
We show that deleting an edge of a 3-cycle in an intrinsically knotted graph gives an intrinsically linked graph.
Investigates intrinsic Lipschitz sections in nonlinear quotient maps.
problem Analyzing intrinsic Lipschitz sections in non-linear quotient maps.
method Introduced Leibniz formula for intrinsic slope under weaker conditions, used properties of intrinsic dilations in Carnot groups, and provided conditions for sum of sections.
result Found conditions for sum of intrinsically Lipschitz sections in Carnot groups of step 2.
We prove that a graph is intrinsically linked in an arbitrary 3-manifold M if and only if it is intrinsically linked in S^3. Also, assuming the Poincare Conjecture, we prove that a graph is intrinsically knotted in M if and only if it is intrinsically knotted in S^3.
Recalls intrinsically harmonic forms and open problems.
problem Open problems related to intrinsically harmonic forms.
method Recalling definitions and known results.
result Clarification of intrinsically harmonic forms and open questions.
Criterion for flat circle bundles using intrinsically harmonic forms.
problem Characterizing flat circle bundles.
method Criterion based on intrinsic harmonicity of a specific form.
result Flatness of a principal circle bundle is equivalent to intrinsic harmonicity of a certain form.
New research shows that the dimension gap between intrinsic and ambient dimensions affects adversarial vulnerability of machine learning models.
problem The mystery of adversarial attacks on machine learning models.
method Introducing two types of adversarial attacks and proving their relationship to the dimension gap.
result The dimension gap between intrinsic and ambient dimensions makes clean-trained models more vulnerable to off-manifold adversarial perturbations.
New method detects intrinsic cross-correlations in non-stationary time series affected by common factors.
problem Bias in cross-correlation analysis due to common external factors.
method Multifractal temporally weighted detrended partial cross-correlation analysis (MF-TWDPCCA).
result MF-TWDPCCA accurately detects intrinsic cross-correlations between non-stationary time series.
Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrins…
Paper analyzes a new Hopf-Lax semigroup in metric spaces.
problem Analyzing a new Hopf-Lax semigroup in metric spaces.
method Using continuous sections of quotient maps and variational problems.
result The 'symmetrized' Hopf-Lax semigroup is a subsolution of Hamilton-Jacobi type equation.
Revisits VIC method to correct intrinsic reward bias in stochastic environments.
problem Intrinsic reward bias in VIC leading to suboptimal solutions.
method Proposes two methods based on transitional probability model and Gaussian mixture model to correct bias.
result Achieves maximal empowerment through corrected intrinsic reward.
BL learns interpretable optimization structures from data.
problem Learning interpretable optimization structures from data.
method BL parameterizes a compositional utility function from intrinsically interpretable modular blocks.
result BL supports architectures from single to hierarchical compositions, modeling hierarchical optimization structures.
Innovative method solves nonconvex optimization on manifolds.
problem Nonconvex optimization problems on Riemannian manifolds.
method Intrinsic Riemannian proximal gradient method.
result Converges for nonconvex or nonembedded problems.
New research finds six bipartite intrinsically knotted graphs with 23 edges.
problem Identifying intrinsically knotted bipartite graphs with 23 edges.
method Analyzing embeddings and graph minors to find minimal intrinsically knotted graphs.
result No minor minimal intrinsically knotted bipartite graph exists with 23 edges.
Biological intelligence can learn to solve many diverse tasks in a data efficient manner by re-using basic knowledge and skills from one task to another. Furthermore, many of such skills are acquired without explicit supervision in an intrinsically driven fashion. This is in contrast to the state-of-the-art reinforceme…