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

3875113150 · May 202619922001200920182026
48 results for Chain rules

Paper explores subdifferential chain rules for matrix factorization and related machine learning models.

problem Clarke subdifferential chain rules for matrix factorization and factorization machines.
method Analyzes conditions for subdifferential chain rules to hold, especially for overparameterized models.
result Subdifferential chain rules hold for matrix factorization and factorization machines under certain conditions.

Develops a chain rule for ReLU networks and extends approximation theory to global error estimates.

problem Applying standard chain rule to ReLU networks and extending approximation results globally.
method Introduces a derivative for ReLU networks and converts bounded domain results to global estimates.
result Extends neural network approximation theory to include regularity properties for ReLU networks.

New training method for neural nets using multilevel entropic regularization.

problem Training efficiency and generalization bounds for neural nets.
method Multilevel relative entropy, chaining mutual information, Gibbs posterior distribution.
result Proves the Gibbs posterior achieves the unique minimum of the empirical risk minimization problem.

In many healthcare settings, intuitive decision rules for risk stratification can help effective hospital resource allocation. This paper introduces a novel variant of decision tree algorithms that produces a chain of decisions, not a general tree. Our algorithm, αα-Carving Decision Chain (ACDC), sequentially carves o…

2016-06-16abs ↗pdf ↗

Predict and explain service failures in supply-chain networks using data models.

problem Predict and explain service failures in supply-chain networks, particularly last-mile pickup and delivery.
method Used supervised classification with Random Forests and Association Rules on a dataset of 500,000 services.
result Classifier reaches an average sensitivity of 0.7 and specificity of 0.7 for 5 types of failure.

Method measures weight similarity in neural networks using normalization and statistical inference.

problem Quantifying weight similarity in non-convex neural networks.
method Chain normalization rule and hypothesis-training-testing statistical inference.
result Weights of identical neural networks converge to similar local solutions.

A conformal procedure improves CoT reasoning by aggregating reasoning paths and calibrating abstention rules.

problem Aggregation uncertainty in chain-of-thought reasoning makes correct answers less reliable.
method Introduces a conformal procedure for CoT reasoning that uses weighted score aggregation and abstention rules.
result Achieves higher selective accuracy with abstention, reducing confident-error rate.

A new stopping rule based on E-values helps efficiently use sampling in Bayesian Deep Ensembles.

problem How long should sampling continue in Bayesian Deep Ensembles to yield significant improvements?
method Formulated as a sequential anytime-valid hypothesis test, using E-values to decide when to stop sampling.
result Only a fraction of the full-chain budget is often required for significant improvements.

This paper is concerned with an optimal stock selling rule under a Markov chain model. The objective is to find an optimal stopping time to sell the stock so as to maximize an expected return. Solutions to the associated variational inequalities are obtained. Closed-form solutions are given in terms of a set of thresho…

2013-09-28abs ↗pdf ↗

A one-to-one correspondence is drawn between law invariant risk measures and divergences, which we define as functionals of pairs of probability measures on arbitrary standard Borel spaces satisfying a few natural properties. Divergences include many classical information divergence measures, such as relative entropy a…

2015-10-23abs ↗pdf ↗

This paper justifies the use of straight-through estimator in training quantized neural nets.

problem Minimizing loss in quantized neural nets with vanishing gradients.
method Introduced straight-through estimator (STE) and proved its effectiveness in two-linear-layer network with binarized ReLU activations.
result Proved that the coarse gradient derived from STE is a descent direction for minimizing population loss.

We propose a new statistical model for computational linguistics. Rather than trying to estimate directly the probability distribution of a random sentence of the language, we define a Markov chain on finite sets of sentences with many finite recurrent communicating classes and define our language model as the invarian…

2013-02-11abs ↗pdf ↗

Study optimal adaptive allocation for multi-armed bandits with Markovian rewards.

problem Optimal adaptive allocation for multi-armed bandits with Markovian rewards.
method Round-robin Kullback-Leibler upper confidence bounds for optimal adaptive allocation.
result Logarithmic dependence of regret on time horizon, asymptotically optimal.

New gradient estimators simplify policy gradient algorithms in reinforcement learning.

problem Challenges in creating effective gradient estimators for reinforcement learning.
method Total derivative rule and graphical models for gradient estimation.
result New gradient estimators lead to improved performance in reinforcement learning.

The paper develops a stationary-distribution theory for Random Forest ensemble size selection.

problem Determining the optimal number of trees in Random Forests.
method Modeling the ensemble size as a birth-death Markov chain and deriving its stationary distribution.
result The stationary ensemble size BB_* scales as O(ε2)O(\varepsilon^{-2}) as ε0\varepsilon\downarrow 0.

This paper analyzes voter coalitions in MakerDAO's decentralized governance.

problem Understanding the governance structure and influence of voter coalitions in DAOs.
method Applied clustering algorithm to voting history of MakerDAO to identify voter coalitions.
result The emergence of a dominant voter coalition signals governance centralization in DAOs.

New method simplifies causal inference with tiered background knowledge.

problem Large equivalence classes of DAGs limit causal information.
method Integrates tiered background knowledge to create 'tiered MPDAGs' with simplified structure.
result Tiered MPDAGs are chain graphs with chordal components, simplifying causal effect estimation.

Knot theory applied to proteins, distinguishing folded linear chains.

problem Classifying proteins as unknots when intra-chain interactions are ignored.
method Developing knot theory for folded linear molecular chains, considering self-bonding, and using Gauss codes and quandles.
result Extended knot theory to distinguish topologies of proteins with intra-chain bonds.

Optimal sample complexity for autoregressive chain-of-thought learning proven.

problem Determining the minimum number of samples needed for accurate autoregressive chain-of-thought learning.
method Proved upper bound on sample complexity using Daniely-Shalev-Shwartz dimension and roll-out stable parity dimension.
result The sample complexity is bounded by the local next-token class rate, with no dependence on rollout length.

Improves sampling quality in model composition using MH-like acceptance rule for score-based diffusion models.

problem Inability to apply MH corrections in score-based diffusion models for model composition.
method Introduces a novel MH-like acceptance rule based on line integration of the score function.
result Relative improvements similar to energy-based models without explicit energy parameterization.

LLMs translate natural language trading intents into correct option strategies using a domain-specific language.

problem Challenges in translating natural language trading intents into correct option strategies due to the complexity of option chain data.
method Introduce Option Query Language (OQL) as a domain-specific intermediate representation to abstract option markets into high-level primitives under grammatical rules. Use LLMs as semantic parsers and validate queries by an engine.
result Significantly improves execution accuracy and logical consistency over direct baselines.

ToolChain-CRC addresses the risk-control problem for retrieval-augmented and tool-using agents under drift.

problem Risk-control problem for retrieval-augmented and tool-using agents under drift.
method ToolChain-CRC uses conformal risk-control under exchangeable calibration runs.
result Trajectory-level risk control keeps accepted-trajectory risk below the target.

Paper bridges matching rules and height functions in aperiodic tilings.

problem Relationship between matching rules and height functions in aperiodic tilings.
method Cochain-first framework to establish equivalence between matching rules, Ammann bar continuity, cycle closure of 1-cochains, and height-function existence.
result Unified framework for aperiodic tilings including Penrose and canonical projection tilings.

New framework compares two stochastic learning dynamics in games.

problem Inability to distinguish between different learning rules leading to the same steady-state behavior.
method Developed a framework for comparative analysis of stochastic learning dynamics with different update rules.
result Identified distinct behaviors in the paths to stochastically stable states for LLL and ML.

ISOMORPH creates a digital twin for supply chain logistics, advancing time-series forecasting benchmarks.

problem Lack of public benchmarks for supply chain logistics time-series forecasting.
method Developed a digital twin simulator with interpretable parameters and modular topology, generating datasets and verifying conservation laws.
result Foundation models achieve MASE values exceeding public benchmarks at low-to-moderate horizons, supporting UQ.

This paper constructs an algebra on a 3-torus with specific properties for fluid dynamics.

problem Constructing an algebraic structure on a 3-torus with specific properties.
method Combining combinatorial graded intersection algebra with Sullivan's and Lawrence-Sullivan-Ranade's subcomplexes.
result The construction of an algebra with specific properties on the 3-torus.

Dynamic abstention improves LLM accuracy by selectively terminating unpromising reasoning.

problem LLMs waste compute on incorrect responses, leading to inefficiency.
method Formal reinforcement learning framework with abstention reward parameter.
result Dynamic abstention outperforms natural baselines in selective accuracy.