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

1122 · Feb 202019922001200920172026
26 results for SAIL

SAIL-RevKL improves SAIL's convergence by regularizing the objective function.

problem Convergence of self-improving online LLM alignment algorithms.
method Proposed SAIL-RevKL, a regularized objective function to improve optimization landscape.
result Proved SAIL-RevKL satisfies the Polyak-Lojasiewicz (PL) condition with near-linear sample complexity.

SAIL improves graph node representation learning by distilling knowledge between graphs.

problem Improving graph node representation learning with GNNs in unsupervised scenarios.
method SAIL framework with intra- and inter-graph knowledge distillation.
result SAIL consistently outperforms state-of-the-art baselines on various benchmark datasets.

Adversarial Imitation Learning (AIL) is a broad family of imitation learning methods designed to mimic expert behaviors from demonstrations. While AIL has shown state-of-the-art performance on imitation learning with only small number of demonstrations, it faces several practical challenges such as potential training i…

2020-02-20abs ↗pdf ↗

SAIL learns from sub-optimal demonstrations to improve sample efficiency in sparse reward tasks.

problem Reducing sample complexity in sparse-rewarded tasks.
method Self-Adaptive Imitation Learning (SAIL) that exploits sub-optimal demonstrations and efficient exploration.
result Significantly improved sample efficiency and better final performance across various tasks.

We establish a close connection between stable commutator length in free groups and the geometry of sails (roughly, the boundary of the convex hull of the set of integer lattice points) in integral polyhedral cones. This connection allows us to show that the scl norm is piecewise rational linear in free products of Abe…

2009-07-21abs ↗pdf ↗

SAIL improves online alignment of large language models with minimal feedback.

problem Offline RLHF methods often lead to sub-optimal performance due to fixed preference datasets.
method SAIL uses bilevel optimization and a single-level first-order method to iteratively refine model alignment.
result SAIL significantly improves alignment performance on open-sourced datasets with minimal computational overhead.

OMLE combines optimism and MLE for efficient sequential decision making.

problem Efficiently solving sequential decision making problems, especially in partially observable settings.
method Combines optimism for exploration and maximum likelihood estimation for model learning.
result OMLE learns near-optimal policies for a wide range of sequential decision making problems.

We study stable commutator length (scl) in free products via surface maps into a wedge of spaces. We prove that scl is piecewise rational linear if it vanishes on each factor of the free product, generalizing the main result in Danny Calegari's paper "Scl, sails and surgery". We further prove that the property of isome…

2016-11-22abs ↗pdf ↗

Paper introduces a differentiable regularizer for condition number to improve neural network stability.

problem Maintaining numerical stability in neural networks to ensure reliable and performant models.
method Introduces a novel differentiable regularizer for the condition number of weight matrices.
result Derives a differentiable formula for the gradient of the regularizer, promoting matrices with low condition numbers.

Nonparametric method measures influence of training images on diffusion model outputs.

problem Quantifying influence of individual training examples on diffusion model outputs.
method Patch-level similarity between generated and training images, using optimal score function.
result Strong attribution performance, matching gradient-based approaches and outperforming baselines.

Paper addresses online alignment of large language models under uncertain preference feedback.

problem Online alignment of large language models with misspecified preference feedback.
method Formulates an oracle-robust objective as a worst-case optimization problem for log-linear policies, and develops projected stochastic composite updates.
result Shows that the robust objective admits an exact closed-form decomposition and achieves O~(ε2)\widetilde{O}(\varepsilon^{-2}) oracle complexity.

End-to-end framework optimizes constrained trajectories using data-driven methods.

problem Optimizing trajectories under constraints with limited dynamics knowledge.
method Data-driven approach decomposes trajectories into function basis, uses maximum a posteriori for optimization, and incorporates linear constraints.
result Commanding results in aeronautics and sailing route optimization.

This paper discusses challenges and opportunities in vessel behavior detection using machine and deep learning.

problem Real-time analysis of vessel behaviors is crucial for maritime safety and protection.
method Comparison of classical machine learning and deep learning approaches for vessel event and anomaly detection.
result Novel methods and tools are needed to address challenges in vessel behavior detection.

Mercat preserves angles to create accurate low-dimensional embeddings.

problem Reconstructing global relationships in low-dimensional embeddings.
method Reconstructing angles between data points to preserve both local and global structures.
result Mercat yields good reconstruction across various experiments and metrics.

Adaptive anchor methods improve multi-modal learning by balancing intra-modal and inter-modal information.

problem Fixed anchor methods limit multi-modal learning by over-reliance on a single modality and inadequate cross-modal correlation.
method Adaptive anchor methods using centroid-based anchors from all modalities.
result Adaptive anchor methods like CentroBind consistently outperform fixed anchor methods across various datasets.

New method provides valid confidence intervals for spatial associations.

problem Limited insight into covariate-response relationships in spatial settings.
method Lipschitz-driven uncertainty quantification for spatial association.
result Valid frequentist confidence intervals for associations in spatial settings.

Study loxodromes and geodesics on rotational surfaces in pseudo-isotropic space.

problem No study on loxodromes in pseudo-isotropic space I_p^3.
method Define pseudo-isotropic angles, derive equations for space-like and time-like loxodromes and geodesics on rotational surfaces.
result Equations for space-like and time-like loxodromes and geodesics on rotational surfaces in pseudo-isotropic space.

Survey on biases in image analysis for industrial safety.

problem Bias in machine learning algorithms affects industrial safety-critical applications.
method Survey and analysis of recent advances in bias detection and mitigation.
result Need for new methods to detect and mitigate biases in image analysis for safety-critical applications.

Paper addresses reward hacking in preference optimization, proposing POWER-DL to improve AI alignment.

problem Reward hacking problem in preference optimization, leading to undesired behaviors.
method POWER-DL combines robust reward maximization and dynamic label updates to mitigate reward hacking.
result POWER-DL consistently outperforms state-of-the-art methods on alignment benchmarks.