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

4795142189 · Jun 202019922001200920172026
48 results for trajectory-level supervision

Trajectory-level supervision allows efficient offline reinforcement learning.

problem Offline reinforcement learning
method Developing a statistical theory for offline policy optimization from trajectory-level labels
result Proving a high-probability guarantee of order O~(H2Csa(π)/n)\widetilde O(H^2\sqrt{C_{sa}(\pi^\star)/n})

Paper resolves the debate on process vs. outcome supervision in reinforcement learning.

problem Distinguishing between process and outcome supervision in reinforcement learning.
method Developed a technical tool (Change of Trajectory Measure Lemma) to show equivalence between outcome and process supervision under standard data coverage assumptions.
result Reinforcement learning through outcome supervision is statistically equivalent to process supervision, up to polynomial factors in horizon.

Meta-algorithm for efficient reinforcement learning from human preferences.

problem Learning from human preference comparisons in Markov decision processes.
method Randomized exploration and experimental design for batch comparison queries.
result Meta-algorithm achieves both regret and last-iterate guarantees with minimal preference queries.

Enhances math problem-solving models with multi-turn preference learning.

problem Improving mathematical problem-solving capabilities of large language models.
method Introduces a multi-turn direct preference learning framework for tool-integrated mathematical reasoning tasks.
result Significant performance improvements in model accuracy on math datasets.

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.

Study shows fast rates for inverse reinforcement learning with linear rewards.

problem Entropy-regularized min-max inverse reinforcement learning in finite-horizon MDPs.
method Structural and statistical analysis of Min-Max-IRL with pseudo-self-concordance.
result Both trajectory-level KL divergence and parameter error decay at O(n1)\mathcal{O}(n^{-1}).

EviTrack improves sequential prediction in delayed disambiguation scenarios.

problem Challenges in sequential prediction with delayed disambiguation where early observations are ambiguous.
method EviTrack operates over latent trajectories, applying evidence- and likelihood-ratio-based selection to delay commitment until supported by data.
result EviTrack outperforms sampling-based baselines in a controlled synthetic benchmark, achieving faster post-disambiguation recovery.

Transformer-based models overfit financial time series data, leading to increased prediction variance.

problem Forecast collapse of transformer-based models under squared loss in financial time series.
method Theoretical analysis and numerical experiments on high-frequency EUR/USD exchange rate data.
result Increased model expressivity in Transformer-based models leads to spurious fluctuations without reducing bias, resulting in higher prediction variance.

QuantaAlpha uses evolutionary algorithms to mine financial alpha robustly across market distributions.

problem Challenges in alpha mining due to market noise and regime shifts.
method Evolutionary framework treating each mining run as a trajectory, mutation, crossover, targeted revision, and reuse of effective patterns.
result Consistent gains over strong baselines and prior systems, achieving high IC and ARR.

Diffusion models simulate molecular dynamics with adjustable accuracy.

problem Simulating molecular dynamics with high accuracy and efficiency.
method Diffusion models as Euler-Maruyama integrators for Langevin dynamics, learning forces from static snapshots.
result Diffusion models generate molecular trajectories with temporal correlations similar to MD simulations.

FLUID uses flows to unify filtering and smoothing for complex systems.

problem Bayesian filtering and smoothing for high-dimensional nonlinear systems.
method FLUID encodes observation histories into a fixed summary statistic, using flows for filtering and smoothing.
result FLUID provides accurate approximations of filtering and smoothing distributions.

Generative model learns to mimic time-series behavior to generate accurate trajectories.

problem Learning generative models for time-series data with accurate multi-step trajectories.
method Contrastive imitation framework combining autoregressive and adversarial elements.
result The method generates accurate and useful samples from real-world datasets.

SupSiam and SupBYOL improve supervised representation learning with ANCL.

problem Improving supervised representation learning with ANCL.
method Proposed supervised ANCL framework leveraging labels to avoid collapse.
result Supervised ANCL improves representation learning across various datasets and tasks.

S4 learns new self-supervision automatically, improving accuracy with less human effort.

problem Lack of direct supervision in machine learning.
method Combines deep learning and probabilistic logic to automatically generate and verify new self-supervision.
result S4 can automatically propose accurate self-supervision, matching supervised methods with less human effort.

Gradient descent trains both layers of a ReLU network to fit a linear model.

problem Training dynamics of a ReLU network to fit a linear target function.
method Jointly training both layers of a one-hidden-layer ReLU network in a realizable setting with Gaussian inputs and labels.
result Gradient descent from a small random initialization converges to a global minimizer at a linear rate with optimal sample complexity.

Paper proposes an algorithm to recover full supervision from weakly labeled data.

problem Machine learning requires expensive data annotation, motivating the use of weak supervision.
method The paper introduces a disambiguation principle and an empirical disambiguation algorithm for partial labelling.
result The algorithm achieves exponential convergence rates under learnability assumptions.

The scarcity of data annotated at the desired level of granularity is a recurring issue in many applications. Significant amounts of effort have been devoted to developing weakly supervised methods tailored to each individual setting, which are often carefully designed to take advantage of the particular properties of …

2015-09-22abs ↗pdf ↗

Traditionally, there are three species of classification: unsupervised, supervised, and semi-supervised. Supervised and semi-supervised classification differ by whether or not weight is given to unlabelled observations in the classification procedure. In unsupervised classification, or clustering, all observations are …

2013-07-13abs ↗pdf ↗

Self-supervised and supervised methods learn similar intermediate visual representations but diverge in final layers.

problem Comparing self-supervised and supervised methods for visual learning.
method Comparison of contrastive self-supervised and supervised methods on simple image data.
result Contrastive and supervised methods learn similar intermediate representations but diverge in final layers.

Optimal and safe semi-supervised learning estimator for high-dimensional data.

problem Improving regression parameter estimation with unlabeled data in high-dimensional settings.
method Established minimax lower bound, proposed optimal and safe semi-supervised estimators.
result Optimal semi-supervised estimator achieves the minimax lower bound.

Survey of self-supervised learning methods in computer vision, NLP, and graph learning.

problem Manual labeling and vulnerability to attacks in supervised learning.
method Generative, contrastive, and generative-contrastive approaches.
result Self-supervised learning achieves high performance in representation learning.

Proposes a framework for semi-supervised continual learning from sequentially arriving data.

problem Learning from data with changing task distribution over time, especially in domains with a mix of labeled and unlabeled data.
method Meta-Consolidation for Continual Semi-Supervised Learning (MCSSL) framework with a hypernetwork and semi-supervised auxiliary classifier.
result Significant improvements in continual semi-supervised learning setting.

Unified framework for semi-supervised learning reduces annotation needs.

problem Sparse annotations and large amounts of unlabeled data in computational pathology.
method S5CL integrates fully-supervised, self-supervised, and semi-supervised learning through hierarchical contrastive losses.
result S5CL improves accuracy and F1-score in histopathological datasets with sparse labels.

We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions. While recent approaches for self-supervised learning have shown the benefits of training on large unlabeled datasets, we find improvements in …

2019-06-17abs ↗pdf ↗

For semi-supervised techniques to be applied safely in practice we at least want methods to outperform their supervised counterparts. We study this question for classification using the well-known quadratic surrogate loss function. Using a projection of the supervised estimate onto a set of constraints imposed by the u…

2016-02-25abs ↗pdf ↗

Hashing has been widely used for large-scale approximate nearest neighbor search because of its storage and search efficiency. Recent work has found that deep supervised hashing can significantly outperform non-deep supervised hashing in many applications. However, most existing deep supervised hashing methods adopt a …

2017-07-26abs ↗pdf ↗

New framework analyzes why more negative samples improve self-supervised learning performance.

problem Inconsistency between theoretical degradation and empirical improvement of downstream supervised tasks with more negative samples.
method Coupon collector's problem framework to analyze self-supervised representation learning with more negative samples.
result Bound can implicitly incorporate supervised loss in self-supervised loss by increasing negative samples.

Maximizing the area under the receiver operating characteristic curve (AUC) is a standard approach to imbalanced classification. So far, various supervised AUC optimization methods have been developed and they are also extended to semi-supervised scenarios to cope with small sample problems. However, existing semi-supe…

2017-05-04abs ↗pdf ↗

PLRM synthesizes labels from mismatched sources for better training sets.

problem Creating labeled training sets is a major challenge in machine learning.
method PLRM uses probabilistic modeling to synthesize labels from indirect supervision sources with different output spaces.
result PLRM outperforms baselines by 2%-9% on various tasks.

New approach combines semi-supervised learning and bandits for better predictions.

problem Online semi-supervised learning with bandit feedback for applications like clinical trials and ad recommendations.
method Adjusted Graph Convolutional Network (GCN) for contextual bandits, with semi-supervised missing rewards imputation.
result Developed multi-GCN embedded contextual bandit algorithms verified on real-world datasets.