The paper identifies collaborations in codebases using commit activity and language usage.
problem Identifying organic team interactions and collaborations in large codebases.
method Embedding and clustering commit activity, language usage, and code identifier topics.
result Restores engineering organization and reveals hidden collaborations.
SafePILCO is a Python tool for safe reinforcement learning.
problem Safe and efficient policy synthesis in reinforcement learning.
method Extends PILCO algorithm with safety features, implemented in Python.
result Safe and data-efficient policy synthesis achieved.
Study replicates market model, finds replication hindered by missing details.
problem Replicating a market model with missing details and limited quantitative reporting.
method Increased simulation runs, bootstrap confidence intervals, and code analysis.
result Achieved relational equivalence for most metrics but rejected quantitative alignment.
This paper presents a method to improve continual learning stability and plasticity.
problem Balancing learning stability and plasticity in deep learning.
method Batch-level Experience Replay with Review approach.
result Achieved 1st place in all three scenarios of the CVPR 2020 CLVision challenge.
Orpheus simplifies deep learning deployment on edge devices.
problem Optimizing deep learning inference on edge devices for efficiency.
method Orpheus is a new framework with a small codebase, minimal dependencies, and easy integration.
result Preliminary results show the effectiveness of Orpheus for inference optimisations.
This work benchmarks MARL algorithms in cooperative tasks.
problem Lack of evaluation tasks and criteria for comparing MARL algorithms.
method Systematic evaluation of three MARL algorithm classes in diverse cooperative tasks.
result Insights into the effectiveness of different learning approaches.
SLM Lab is a framework for reproducible RL research with modular algorithms.
problem Reproducibility in deep reinforcement learning.
method Modular software framework for RL algorithms, synchronous/asynchronous execution, hyperparameter search, result analysis.
result Comprehensive benchmark and novel RL algorithms (e.g., discrete-AC variant, hybrid training method).
This study evaluates zero-shot LLMs in finance, finding ChatGPT performs well but fine-tuned models are better.
problem Evaluating zero-shot LLMs in financial tasks.
method Comparison of ChatGPT and fine-tuned models on annotated data.
result Fine-tuned models generally outperform zero-shot LLMs.
New algorithms improve time series prediction with uncertainty quantification.
problem Uncertainty quantification for time series prediction.
method Combines conformal prediction and control theory for online, adaptive forecasting.
result Improves coverage over ensemble forecasters in real-world applications.
Paper examines Go AI robustness against adversarial attacks.
problem Superhuman Go AIs are vulnerable to simple adversarial strategies.
method Three defenses tested: adversarial training, iterated adversarial training, and changing network architecture.
result No defense is robust against newly trained adversaries, and attacks are similar to cyclic attacks.
This work uses a scalable approach to identify partially observed nonlinear systems.
problem Offline identification of partially observed nonlinear systems.
method Certainty-equivalent expectation-maximization (CEEM) as block coordinate-ascent.
result The CEEM approach can identify high-dimensional systems reliably and efficiently.
Unified framework evaluates synthetic financial data models.
problem Data scarcity and confidentiality in finance hinder model development and testing.
method Multi-criteria evaluation of three generative paradigms: ARIMA-GARCH, VAEs, and TimeGAN.
result TimeGAN achieves the best balance between realism and temporal coherence.
Spectral measurements reveal hidden representation geometry in language model training.
problem Hidden internal representation in language model training is hard to examine.
method Empirical protocol using activation covariance and per-sample gradient SVD spectra.
result Batch size affects representation geometry, and activation spectra predict token efficiency.
GPflux simplifies deep Gaussian processes for Python.
problem Challenges in implementing deep Gaussian processes.
method Python library for Bayesian deep learning with DGPs.
result Efficient, modular, and extensible library for DGPs.
Study examines bias in language models across multiple languages.
problem Assessing bias in language models across different languages.
method Semi-automatically translated data sets into multiple languages, analyzed mono- and multilingual models.
result Notable differences in bias across languages, with Turkish models showing least stereotypes.
Quantum circuits optimize financial portfolios faster than classical methods.
problem Dynamic portfolio optimization in financial markets.
method Variational Quantum Circuits for reinforcement learning.
result Quantum agents outperform classical RL models in risk-adjusted performance.
PaRoT simplifies robust training for deep neural networks.
problem Training deep neural networks to be robust to small input changes.
method Developed a practical framework on TensorFlow for robust training without code modifications.
result PaRoT's performance is comparable to existing methods and is easy to use on real-world models.
A new catnat function improves gradient descent for categorical variables.
problem Gradient descent challenges with discrete latent categorical variables.
method Replaced softmax with catnat, a hierarchical binary split function.
result Catnat function offers significant advantages in gradient descent.
The paper improves cryptocurrency price forecasting using deep learning and NLP on financial, blockchain, and social media data.
problem Improving cryptocurrency price forecasting accuracy and profitability.
method Integrates financial, blockchain, and social media data; applies BART MNLI model for sentiment analysis; uses deep learning NLP models; compares with traditional methods; uses local extrema as predictive targets.
result Significantly improves forecasting accuracy and profitability of cryptocurrency price predictions.
MuonEq improves training of matrix-valued parameters by rebalancing momentum before orthogonalization.
problem Training matrix-valued parameters with orthogonalized-update optimizers like Muon.
method MuonEq introduces three lightweight pre-orthogonalization equilibration schemes: two-sided row/column normalization (RC), row normalization (R), and column normalization (C).
result Row/column normalization acts as a zeroth-order surrogate for whitening and improves the geometry seen by orthogonalization.
Tutorial on estimating PD using survival analysis under IFRS 9.
problem Dynamic estimation of credit losses under IFRS 9.
method Discrete-time survival analysis for estimating PD.
result Development of a comprehensive tutorial and diagnostic measures.
Study accelerates NAS research with a large dataset of ZC proxies.
problem Speeding up neural architecture search with ZC proxies.
method Created NAS-Bench-Suite, evaluated 13 ZC proxies across 28 tasks, and provided a unified codebase.
result ZC proxies capture substantial complementary information and can improve NAS algorithm performance.
LLMs learn probability density functions in-context, showing distinct learning trajectories.
problem Density estimation of time series data in LLMs.
method Intensive Principal Component Analysis (InPCA) to visualize and analyze LLMs' learning dynamics.
result LLMs follow similar learning trajectories in a low-dimensional InPCA space, distinct from traditional methods.
Paper compares DML methods fairly, finds older ones perform better.
problem Fair comparison of deep metric learning methods.
method Unified implementation of 12 DML algorithms under same conditions.
result Several older DML methods perform significantly better than previously believed.
EduGym simplifies reinforcement learning education for students.
problem Students struggle to translate between equations and code in reinforcement learning.
method EduGym provides educational environments and interactive notebooks.
result 86% of students and researchers find EduGym useful for education.
YRC-Bench benchmarks AI agents learning to collaborate with experts.
problem Learning to recognize when to consult an expert in novel situations.
method Validation strategy and proposer-validator decomposition.
result Insights for future AI safety research.
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device? Neural architecture search (NAS) has revolutionized the design of hardware-efficient ConvNets by automating this process. However, the NAS problem remains challen…
Unified benchmark for GLAD and GLOD methods across 35 datasets.
problem Gap between GLAD and GLOD research due to distinct evaluation setups.
method Comprehensive evaluation framework that unifies GLAD and GLOD.
result Multi-dimensional analyses of existing methods' strengths and limitations.
RETINA Benchmark evaluates Bayesian deep learning on diabetic retinopathy detection.
problem Reliable uncertainty quantification for deep learning models in medical applications.
method Design and evaluation of a real-world diabetic retinopathy dataset and tasks.
result Benchmarking of Bayesian deep learning methods on diabetic retinopathy detection tasks.
The study examines Cox models for lifetime loan default risk, addressing biased estimates by incorporating recurrent events.
problem Ignoring recurrent default events in Cox models leads to biased and inaccurate PD estimates.
method Investigates and compares different Cox models (Andersen-Gill and Prentice-Williams-Peterson) for lifetime loan default risk.
result The Andersen-Gill model underperforms compared to the Prentice-Williams-Person model and the time to first default model.
Source code reviews are manual, time-consuming, and expensive. Human involvement should be focused on analyzing the most relevant aspects of the program, such as logic and maintainability, rather than amending style, syntax, or formatting defects. Some tools with linting capabilities can format code automatically and r…
Conformal prediction provides distribution-free uncertainty quantification for black-box models.
problem Uncertainty quantification for high-risk machine learning applications.
method Conformal prediction creates valid uncertainty sets without distributional assumptions.
result Sets contain the ground truth with a specified probability, e.g., 90%.
This paper shows that scientific discovery can be efficiently learned via compositional function trees, reducing the sample complexity.
problem Statistical and computational intractability of scientific discovery via symbolic regression.
method PAC learning approach focusing on compositional function trees built from a finite vocabulary of smooth operators.
result The Rademacher complexity and excess risk are controlled by depth and Lipschitz constants of the base operators, leading to finite-union bounds and high-probability risk bounds.
HyperINF improves influence function estimation for large models with better accuracy and efficiency.
problem Inaccurate and computationally expensive influence function estimation for large-scale models.
method HyperINF leverages Schulz's iterative algorithm and GFIM for low-rank approximation of Hessian matrix.
result HyperINF achieves superior accuracy and performance compared to existing methods on LoRA-tuned models.
Bayesian approach infers signaling pathways from data.
problem Accurately understand cellular regulation processes.
method Dynamic Bayesian Network structure estimation using Markov Chain Monte Carlo.
result Efficient sampling of sparse graphs improves inference.
GEMSS discovers multiple sparse solutions in high-dimensional data.
problem Identifying multiple sparse feature combinations in high-dimensional, underdetermined systems.
method GEMSS (Gaussian Ensemble for Multiple Sparse Solutions) uses a structured spike-and-slab prior, mixture of Gaussians, and Jaccard-based penalty to optimize a single objective function via stochastic gradient descent.
result GEMSS consistently outperforms five feature selection methods on 128 experiments and real-world datasets.
A RL framework for hedging equity index options with realistic costs.
problem Dynamic hedging of equity index option exposures under transaction costs.
method Reinforcement Learning (RL) with a leak-free environment, cost-aware reward function, and stochastic actor-critic agent.
result The RL policy improves risk-adjusted performance compared to no-hedge, momentum, and volatility-targeting baselines.
A new metric FRD improves comparing medical images.
problem Comparing medical images for distribution or domain differences.
method Developed a new metric FRD using standardized radiomic features.
result FRD outperforms other metrics in various medical imaging applications.
A new approach for specifying and synthesizing subroutines for optimizing metrics.
problem Specifying and optimizing subroutines for various metrics.
method Formalizing programming by rewards (PBR), using continuous-optimization techniques to synthesize decision functions as if-then-else programs.
result Synthesized decision functions are optimal in cases when rewards have nice properties.
Single-Path NAS reduces NAS search cost to 3 hours, achieving state-of-the-art mobile image classification.
problem Efficiently automate ConvNet design under mobile latency constraints.
method Single-Path NAS, using one single-path ConvNet with shared parameters.
result Achieves state-of-the-art top-1 ImageNet accuracy (75.62%) in 8 epochs (24 TPU-hours).
Tabular data analysis shows GBDTs and NNs perform similarly on most datasets.
problem Determining when NNs outperform GBDTs on tabular data.
method Large-scale comparison of 19 algorithms across 176 datasets.
result For many datasets, GBDTs and NNs perform similarly, with hyperparameter tuning often more important than algorithm choice.