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.

168,742 papers · 148 categories

Trend · papers per month

183366549732 · Jun 202019922001200920172026
48 results for representation cost theory

Study learns state representations from observations for control, proving guarantees.

problem Learning state representations from high-dimensional observations for control.
method Cost-driven approach, learning latent state model to predict costs.
result Proves finite-sample guarantees for near-optimal state representation and controller.

This work adapts RDT for mental program construction, showing benefits and costs.

problem Applying RDT to mental programs with trade-offs between description length, error, and computational costs.
method Proposed a three-way trade-off and used simulations and partial information decomposition.
result Constructing a shared program library provides global benefits but is sensitive to curricula.

Develops risk measures for markets with constraints and costs.

problem Risk measures in markets with portfolio constraints and transaction costs.
method Embeds portfolio constraints and transaction costs into securities market; provides comprehensive analysis of risk measures properties.
result Establishes dual representations for convex and quasiconvex risk measures.

This paper examines allocation mechanisms in markets with transfer costs, showing how these costs affect economic efficiency.

problem Transfer costs in decentralized exchange markets reduce economic efficiency.
method An axiomatic study of allocation mechanisms in the presence of transfer costs, providing robust and conditional mean allocation mechanisms.
result Robust and conditional mean allocation mechanisms are identified, relating to risk sharing in agent pools.

Poisson variational autoencoders introduce a metabolic cost term that penalizes high baseline activity.

problem Energy constraints in computation.
method Poisson variational autoencoders with a Kullback-Leibler divergence term proportional to firing rates.
result Poisson variational autoencoders introduce a metabolic cost term that penalizes high baseline activity.

DeepAveragers solves offline RL by solving derived MDPs from static data.

problem Offline reinforcement learning with limited data.
method Solves derived non-parametric MDPs (DAC-MDPs) using deep representations and costs for under-represented parts.
result The approach can lower-bound performance and scale to complex offline RL problems.

Representation costs in data science: Unifying function-space views of parametric methods

problem Analyzing representation costs of parametric data-fitting methods
method Developing a general framework for analyzing representation costs through parameter-space regularizers
result Proving that many natural results hold in this abstract setting, including representer theorems for parametric methods on their native spaces

Study cost-driven state representation learning for control from partial observations.

problem Learning state representation for control from partial and high-dimensional observations.
method Cost-driven state representation learning via predicting cumulative costs.
result Established finite-sample guarantees for near-optimal representation and controller.

It has long been recognized that the invariance and equivariance properties of a representation are critically important for success in many vision tasks. In this paper we present Steerable Convolutional Neural Networks, an efficient and flexible class of equivariant convolutional networks. We show that steerable CNNs …

2016-12-27abs ↗pdf ↗

Quantized-TinyLLaVA reduces communication costs in split learning for multimodal models.

problem High communication costs in split learning for multimodal models.
method Integrates a compression module that quantizes intermediate features into discrete representations before transmission.
result Achieves an approximate 87.5% reduction in communication overhead with 2-bit quantization.

A new method uses algebraic insights to create approximately equivariant networks without complex architectures.

problem Designing equivariant neural networks with complex architectures and high computational cost.
method Imposes the group's regular representation as an inductive bias via an auxiliary loss, adding no learnable parameters.
result Matches or outperforms specialized models in several cases, even for infinite groups.

The study extends SPT to account for real-world transaction costs, improving portfolio performance.

problem Real-world transaction costs affect portfolio performance, especially during market stress.
method Developed a continuous-time model with stochastic transaction costs and derived lower bounds for cost-adjusted wealth.
result Functionally generated portfolios can still achieve relative arbitrage after accounting for transaction costs.

A deep reinforcement learning method for cost-sensitive portfolio selection.

problem Non-stationary price series and complex asset correlations make feature learning hard, and practical cost constraints are not considered.
method A two-stream portfolio policy network and a cost-sensitive reward function are developed using deep reinforcement learning.
result The method achieves superior performance in profitability, cost-sensitivity, and representation abilities.

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.

The paper solves a utility-based hedging problem with quadratic costs.

problem Optimal trading strategy for hedging European contingent claims with quadratic transaction costs.
method Duality theory applied to exponential utility maximization problem.
result Explicit computation of optimal trading strategy for quadratic payoffs.

The paper develops a method to learn navigation costs from expert demonstrations in partially observable environments.

problem Learning navigation costs from expert demonstrations in partially observable environments.
method Develops a cost function representation composed of a probabilistic occupancy encoder and a cost encoder, optimized by differentiating the error between demonstrated controls and a control policy computed from the cost encoder.
result The method outperforms baseline IRL algorithms in robot navigation tasks, improving both training and test-time efficiency.

Despite recent advances in architectures for mobile devices, deep learning computational requirements remains prohibitive for most embedded devices. To address that issue, we envision sharing the computational costs of inference between local devices and the cloud, taking advantage of the compression performed by the f…

2019-11-23abs ↗pdf ↗

Foundation models fail to preserve continuous geometry, identified as the Geometric Alignment Tax.

problem Continuous geometry is lost in foundation models due to discrete categorical bottlenecks.
method Controlled ablations on synthetic systems and evaluation of 14 biological models using rate-distortion theory and MINE.
result Replacing cross-entropy with a continuous head reduces geometric distortion by up to 8.5x.

Kendall transformation converts continuous data into categorical vectors for robust information theory.

problem Handling small number of observations and preserving ranking in continuous data.
method Kendall transformation converts ordered features into categorical vectors of pairwise order relations.
result Kendall transformation makes information theory methods applicable to continuous data robustly.

A new neural topic model using optimal transport improves document representation and topic coherence.

problem Challenges in achieving good document representation and coherent/diverse topics in existing NTMs.
method Proposes a neural topic model via optimal transport, learning topic distribution by minimising OT distance to document word distributions.
result Significantly outperforms state-of-the-art NTMs on discovering coherent and diverse topics.

For portfolio optimisation under proportional transaction costs, we provide a duality theory for general cadlag price processes. In this setting, we prove the existence of a dual optimiser as well as a shadow price process in a generalised sense. This shadow price is defined via a "sandwiched" process consisting of a p…

2014-08-26abs ↗pdf ↗

Based on the analogies between knot theory and number theory, we study a deformation theory for SL_2-representations of knot groups, following after Mazur's deformation theory of Galois representations. Firstly, by employing the pseudo-SL_2-representations, we prove the existence of the universal deformation of a given…

2014-09-11abs ↗pdf ↗

Optimizes communication in federated learning using rate-distortion theory.

problem Reduces communication cost in federated learning while maintaining model accuracy.
method Applies rate-distortion theory to model updates, proposing distortion as a proxy for accuracy.
result Near-optimal communication reduction, outperforming other methods on a FL benchmark.

Trading algorithms that execute large orders are susceptible to exploitation by order anticipation strategies. This paper studies the influence of order anticipation strategies in a multi-investor model of optimal execution under transient price impact. Existence and uniqueness of a Nash equilibrium is established unde…

2016-09-02abs ↗pdf ↗

Unified theory of deep neural networks with diverse activations.

problem Understanding the relationship between depth and complexity in deep neural networks.
method Developed a unified function space theory for deep networks with various activations.
result Unified theory provides meaningful complexity for deep networks with diverse activations.

Paper proposes SDRL to improve continual learning with less computational cost.

problem Catastrophic forgetting in continual learning.
method SDRL method that refines gradients from memorized samples to reduce gradient diversity.
result SDRL shows better performance than state-of-the-art methods on multiple benchmark tasks.

New method AnInfoNCE uncovers latent factors in contrastive learning with practical variability.

problem Theoretical assumptions of contrastive learning loss overlook practical variability in positive pairs.
method AnInfoNCE, a generalization of InfoNCE, models anisotropic variability to uncover latent factors.
result AnInfoNCE increases recovery of latent factors in CIFAR10 and ImageNet, albeit at the cost of accuracy.

Adding linear layers to ReLU networks favors functions with low mixed variation.

problem Understanding function space bias in overparameterized neural networks.
method Examined a family of networks with varying depths and same capacity but different representation costs, focusing on the effect of adding linear layers to the input side.
result Adding linear layers to shallow ReLU networks results in a bias towards functions with low mixed variation, which can be well approximated by single- or multi-index models.