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.

168,657 papers · 148 categories

Trend · papers per month

50100150200 · Jun 202019922001200920172026
48 results for policy regularisation

This work optimizes RL algorithms using entropy regularisation for continuous-time LQ problems.

problem Designing RL algorithms to balance exploration and exploitation in noisy environments.
method Entropy regularisation in two formulations: exploratory control and proximal policy update.
result Regret of O(N)\mathcal{O}(\sqrt{N}) for both learning algorithms over NN episodes.

SPReD uses uncertainty to decide imitation from demonstrations.

problem Learning from sparse rewards with few demonstrations.
method Ensemble methods to model Q-value distributions, probabilistic and advantage-based uncertainty quantification.
result Significant gains in reinforcement learning across multiple tasks.

Study uses actor-critic method for continuous-time mean-field control with entropy regularisation.

problem Continuous-time mean-field control in reinforcement learning.
method Actor-critic approach with entropy regularisation, value function alternation, and Wasserstein space parametrisation.
result Derives exact parametrisation of actor and critic functions in linear-quadratic mean-field framework.

Theory for RLHF generalization under reward shift and clipped KL.

problem Theoretical understanding of RLHF generalization, especially with reward shift and clipped KL.
method Developed generalization theory for RLHF, accounting for reward shift and clipped KL.
result Presented generalization bounds for RLHF, suggesting generalization error from sampling, reward shift, and KL clipping.

ICCNLS models complex relationships as convex and concave components.

problem Complex input-output relationships with affine ambiguity.
method Sub-gradient constrained affine functions, global orthogonality constraints, L1, L2, and elastic net regularisation.
result Improved predictive accuracy and model simplicity compared to conventional methods.

We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt in \textit{continuously} changing environments. In our \textit{policy consolidati…

2019-02-01abs ↗pdf ↗

This paper shows RL with KL penalties is equivalent to Bayesian inference for fine-tuning LMs.

problem Fine-tuning large language models to avoid undesirable features.
method Analyzed KL-regularized RL and showed it's equivalent to variational inference.
result KL-regularized RL avoids distribution collapse and is more insightful as Bayesian inference.

This paper improves inverse problem solving with weakly convex regularisers and proves convergence.

problem Improving solution methods for inverse problems.
method Generalised formulation of convergent regularisation using weakly convex regularisers, and proof of convergence for primal-dual hybrid gradient method.
result Proves convergence of primal-dual hybrid gradient method for variational problems and shows improved performance with IWCNNs.

Paper analyzes convergence of dynamic policy gradient for MDPs, improving performance in finite-time problems.

problem Optimal policies in finite-time MDPs are not stationary and require epoch-specific training.
method Introduces dynamic policy gradient combining dynamic programming and policy gradient, analyzes convergence for softmax parametrisation.
result Dynamic policy gradient training exploits finite-time structure, leading to better convergence bounds.

GNIs induce a regulariser that penalizes high-frequency components in neural network activations.

problem Understanding the regularizing effect of Gaussian noise injections on neural network activations.
method Deriving the explicit regularizer by marginalizing out injected noise and analyzing its effect in the Fourier domain.
result GNIs induce a regularizer that produces calibrated classifiers with large margins.

We propose a probabilistic framework to directly insert prior knowledge in reinforcement learning (RL) algorithms by defining the behaviour policy as a Bayesian posterior distribution. Such a posterior combines task specific information with prior knowledge, thus allowing to achieve transfer learning across tasks. The …

2018-09-30abs ↗pdf ↗

A Python package solves source duplication in single channel LVMs using spectral regularisation.

problem Source duplication in LVMs hampers their practical use in single channel applications.
method Spectral regularisation term added to address source duplication issue.
result Spectral regularisation framework enables easier investigation and utilisation of LVMs.

New framework monitors neural network training and reveals regularisation mechanisms.

problem Overfitting in neural networks and the need for explicit regularizers.
method Model Gradient Similarity (MGS) framework to measure and monitor regularisation.
result Explicit regularizers increase Model Gradient Similarity (MGS).

This work uncovers algorithm-dependent regularisation in diffusion models.

problem Understanding and improving generalisation in high-dimensional diffusion models.
method Algorithmic stability and score stability analysis.
result Identifies multiple sources of implicit regularisation unique to diffusion models.

The transfer of knowledge from one policy to another is an important tool in Deep Reinforcement Learning. This process, referred to as distillation, has been used to great success, for example, by enhancing the optimisation of agents, leading to stronger performance faster, on harder domains [26, 32, 5, 8]. Despite the…

2019-02-06abs ↗pdf ↗

Despite recent advances in regularisation theory, the issue of parameter selection still remains a challenge for most applications. In a recent work the framework of statistical learning was used to approximate the optimal Tikhonov regularisation parameter from noisy data. In this work, we improve their results and ext…

2018-09-23abs ↗pdf ↗

The problem of adversarial examples has highlighted the need for a theory of regularisation that is general enough to apply to exotic function classes, such as universal approximators. In response, we give a very general equality result regarding the relationship between distributional robustness and regularisation, as…

2020-02-11abs ↗pdf ↗

An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks. In general, however, it is unclear how to compose skills in a principled way. We provide a "recipe" for optimal value function composition in entropy-regularised reinforcement learning (RL) and then exten…

2018-07-12abs ↗pdf ↗

Novel approach finds implicit regularisation in two-player games using BEA.

problem Understanding implicit regularisation in two-player games.
method Using backward error analysis to construct continuous-time flows with gradient-eligible vector fields.
result Identifies new implicit regularisation effects in two-player games.

Regularization preserves topological data structure in autoencoders.

problem Ensuring topological data structure preservation in autoencoders.
method Regularization using Legendre nodes to preserve manifold embedding.
result Regularized autoencoders ensure one-to-one embedding of data manifolds.

Investigates gradient descent dynamics and introduces new regularisation methods.

problem Understanding and mitigating gradient descent instabilities and interactions with smoothness regularisation.
method Derives continuous-time flows to account for discretisation drift, constructs learning rate schedules and regularisers.
result New regularisation methods improve performance in reinforcement learning.

Improved RL training for DMs reduces mode collapse and preserves diversity.

problem Mode collapse and training instability in RL fine-tuned diffusion models.
method Dynamic hierarchical RL training with sliding-window parameter regularisation.
result Models trained with HRF achieve better preservation of diversity in downstream tasks.

Researchers compare different gradient methods for ridge regression, finding conjugate gradients have similar performance.

problem Comparing statistical properties of different gradient methods in ridge regression.
method Explicit non-standard error decomposition to bound prediction error of conjugate gradient iterates.
result Conjugate gradient iterates share optimality properties with gradient flow and ridge regression up to a constant factor.

Study on GD and SGD over diagonal networks, focusing on stepsizes and regularisation.

problem Understanding the impact of stochasticity and large stepsizes on gradient descent and SGD solutions.
method Investigation of GD and SGD over diagonal linear networks with macroscopic stepsizes, proving convergence and characterizing solutions.
result Large stepsizes consistently benefit SGD for sparse regression problems, but can hinder GD recovery of sparse solutions, especially in the edge of stability regime.

This work shows how penalising bias terms in norm regularisation leads to sparse solutions.

problem Understanding the relation between parameter norm regularization and the sparsity of neural network solutions.
method Analyzes one hidden ReLU layer networks with unidimensional data, showing the norm required for function representation and the importance of the bias term's norm.
result Penalising the bias terms in regularisation leads to sparse solutions, enforcing the uniqueness and sparsity of the minimal norm interpolator.

Regularizes ML algorithms for robust multivariate analysis against distribution shifts.

problem Ensuring robustness of multivariate analysis algorithms against distribution shifts.
method Integrates a causal regularisation term into the loss function of multivariate analysis algorithms.
result Demonstrates improved out-of-distribution generalisation with reduced-rank regression and partial least squares.

Study on how noise and variation-norm regularisation help shallow ReLU networks use fewer neurons.

problem Understanding how shallow ReLU networks use a finite number of neurons in the infinitely wide limit.
method Analysis of two regularisation strategies: noise injection and variation-norm.
result Both regularisation methods minimize functions with a finite number of neurons, regardless of overparametrisation.

Paper studies particle method for LSV model calibration, proving convergence and error bounds.

problem Calibration of local-stochastic volatility models with open well-posedness question.
method Regularized Euler--Maruyama scheme for particle approximation of McKean--Vlasov dynamics.
result Strong convergence of the Euler--Maruyama scheme with rate 1/2 in step-size.

Improves BC policies by generating new plausible trajectories.

problem Sub-optimal data quality in BC leads to poor policy performance.
method Trajectory Stitching (TS) generates new plausible transitions.
result TS significantly improves behavioural policies over original data.

DML-IV improves IV regression for learning decision policies by reducing bias.

problem Spurious correlations in offline datasets caused by hidden confounders.
method Double/debiased machine learning (DML) framework to reduce bias in two-stage IV regression.
result DML-IV outperforms state-of-the-art methods and learns high-performing policies.

New conditions show proxy data can improve policy learning in sparse expert data contexts.

problem Improving sample complexity of policy learning with sparse expert data.
method Sufficient conditions for proxy data to improve sample complexity, adaptable to LLMs.
result Provable improvement in sample complexity for policy learning with proxy data.

New insights into how neural networks learn features, especially when they are very wide.

problem Understanding how gradient flow in wide neural networks selects solutions, especially in the feature-learning regime.
method Axiomatizing the canonical regularizer as a function-space energy and lift, and deriving geodesic ridge for the feature-learning regime.
result Gradient flow in feature-learning networks biases towards ridge regularization, distorting the inductive bias and damaging pretrained networks.

Study on neural networks with regularisation and its impact on training dynamics.

problem Understanding the dynamics of neural networks with regularization.
method Established explicit dynamics for neural networks with a regularizing term, linearizing around initialisation.
result The regularisation term modifies the standard NTK dynamics, leading to new insights into network training.

Regularising for invariance to data augmentation improves machine learning models.

problem Improving generalization in machine learning models through data augmentation.
method Explicit regularisation to encourage invariance at the level of individual model predictions.
result Explicit regularisation improves generalization and equalizes performance differences between objectives.

Paper shows equivalence between two alignment methods and introduces a new algorithm.

problem Ensuring human alignment of large language models for useful, safe, and pleasant user experience.
method Introduces IPO-MD algorithm, showing equivalence between IPO and Nash-MD methods.
result Equivalence between IPO and Nash-MD methods proven when considering online version of IPO.

Unified understanding of three continual learning regularisation methods.

problem Maintaining knowledge of earlier tasks without re-accessing them.
method Three regularisation approaches: Elastic Weight Consolidation (EWC), Synaptic Intelligence (SI), and Memory Aware Synapses (MAS).
result EWC, SI, and MAS are linked to the same theoretical quantity, the square root of the Fisher Information.

The paper studies mm-positive currents and line bundles on complex manifolds.

problem Understanding mm-positive currents and their properties on complex manifolds.
method Introducing mm-plurisubharmonic functions, proving vanishing theorems, and regularisation theorems using viscosity solutions.
result Global and local regularisation theorems for mm-semi-positive currents.