arXiv research

FEET protocol evaluates foundation models across three scenarios.

Proposes clustering as a new evaluation method for clinical knowledge embedding.

New algorithms for model selection in off-policy evaluation of reinforcement learning.

New benchmark protocol evaluates neural network optimizers for efficiency and data shift sensitivity.

A new protocol evaluates small machine learning improvements conservatively.

The paper critiques current time series classification evaluation methods.

This paper critiques flawed MVTS anomaly detection evaluation methods and proposes a simple baseline.

New federated learning protocols resist Byzantine failures and offer privacy guarantees.

New protocol evaluates synthetic data for temporal consistency.

Knowledge bases contribute to many web search and mining tasks, yet they are often incomplete. To add missing facts to a given knowledge base, various embedding models have been proposed in the recent literature. Perhaps surprisingly, relatively simple models with limited expressiveness often performed remarkably well …

Compound Finance optimizes risk metrics for V3 protocol using Chainrisk simulations.

Protocol for constructing tailored evaluation datasets for semantic models.

Benchmark detects decision-time leakage in financial backtests.

NAS evaluation is hard due to lack of standard protocols.

This study aims to improve communication between fragmented blockchain systems in finance.

Swarm systems constitute a challenging problem for reinforcement learning (RL) as the algorithm needs to learn decentralized control policies that can cope with limited local sensing and communication abilities of the agents. While it is often difficult to directly define the behavior of the agents, simple communicatio…

GraphBench creates a unified benchmark for graph learning tasks.

Paper develops LDP protocols for computing U-statistics with various error bounds.

We propose an efficient protocol for decentralized training of deep neural networks from distributed data sources. The proposed protocol allows to handle different phases of model training equally well and to quickly adapt to concept drifts. This leads to a reduction of communication by an order of magnitude compared t…

SIREN protocol corrects optimistic winner's scores in LLM evaluation.

Study finds no significant short-term impact on liquidity supply after protocol fees were reduced.

Graph learning categorizes DeFi services into similar functionalities.

Deep reinforcement learning algorithms have shown an impressive ability to learn complex control policies in high-dimensional tasks. However, despite the ever-increasing performance on popular benchmarks, policies learned by deep reinforcement learning algorithms can struggle to generalize when evaluated in remarkably …

The paper examines how decentralized credit curators have taken over risk management from traditional protocols.

Auto$.$gov uses RL to automate DeFi governance, improving security and profitability.

Paper explores anchoring for vision models, improving generalization and safety.

RL Unplugged benchmarks offline RL methods across diverse domains.

Study evaluates bias mitigation methods in deep learning, finds they often exploit hidden biases.

Convolutional neural networks (CNNs) have shown promising results on several segmentation tasks in magnetic resonance (MR) images. However, the accuracy of CNNs may degrade severely when segmenting images acquired with different scanners and/or protocols as compared to the training data, thus limiting their practical u…

The paper shows how ignoring temporal context in recommender systems evaluation leads to false confidence, proposing a method to embed temporal context.

A framework for evaluating and benchmarking concept drift detection methods

New study on time series anomaly detection shows overlapping inference improves performance.

The paper introduces a protocol for including advice in robot interaction to improve performance.

A new protocol corrects confounding effects to measure alignment-induced activation shifts accurately.

FinReflectKG - EvalBench benchmarks financial KG extraction from SEC 10-K filings.

This paper explores how interactive protocols enhance local differential privacy.

This paper improves domain adaptation methods using graph embedding.

Maker Protocol manages Dai stable coin on Ethereum blockchain.

This paper examines interest rates and market efficiency in DeFi loanable funds protocols.

The paper analyzes how mutable blockchain protocols affect miner behavior and strategic stability.

Protocol minimizes disclosure in classification tasks.

This study measures liquidity risks in Aave, a blockchain lending protocol.

Hybrid LLM generates synthetic data preserving causal parameters.

Paper presents a risk management framework for blockchain protocols.

Feedback alignment methods need to be evaluated for accuracy and gradient cosine similarity.

Study analyzes risk management in Aave and Compound lending protocols, finding v3 better than v2.

Distributing Neural Network training is of particular interest for several reasons including scaling using computing clusters, training at data sources such as IOT devices and edge servers, utilizing underutilized resources across heterogeneous environments, and so on. Most contemporary approaches primarily address sca…

Objective: Anemia is a frequent comorbidity in hemodialysis patients that can be successfully treated by administering erythropoiesis-stimulating agents (ESAs). ESAs dosing is currently based on clinical protocols that often do not account for the high inter- and intra-individual variability in the patient's response. …