Unified framework to bridge human and LLM judgments.
problem Systematic discrepancies between human and LLM evaluations.
method Latent human preference score and linear transformations of covariates.
result Higher agreement with human ratings and exposure of systematic gaps.
NATS-Bench benchmarks NAS algorithms for architecture topology and size.
problem Incomparable performance of NAS algorithms due to different search spaces and training setups.
method Unified benchmarking platform for architecture topology and size searching.
result Validated benchmark for 15,625 topology and 32,768 size candidates.
SKADA-bench evaluates unsupervised DA methods across diverse modalities.
problem Evaluating unsupervised DA methods on diverse modalities with realistic validation.
method Nested cross-validation and unsupervised model selection scores.
result Highlights the importance of realistic validation and provides practical guidance.
New benchmarks provide full training data for NAS research.
problem Limited training data on popular benchmarks restricts multi-fidelity techniques.
method SVD and noise modeling to create surrogate benchmarks with full training info.
result Learning curve extrapolation framework improves single-fidelity algorithms.
LOB-Bench benchmarks generative AI for financial data, outperforming traditional models.
problem Lack of consensus on evaluating generative AI models for financial data.
method Python-based benchmark with LOB statistics and market impact metrics.
result Generative autoregressive models outperform traditional models in LOB data.
NAS-Bench-Suite simplifies NAS evaluation across diverse tasks.
problem Limited and inconsistent NAS benchmarks hinder research reproducibility.
method Developed a comprehensive, extensible NAS benchmark suite.
result Many NAS conclusions do not generalize across different benchmarks.
SurvHTE-Bench benchmarks HTE estimation in survival analysis with diverse datasets.
problem Challenges in estimating HTEs from right-censored survival data.
method Modular synthetic datasets, semi-synthetic datasets, and real-world datasets.
result First rigorous comparison of survival HTE methods under diverse conditions.
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.
BRP-NAS uses GCNs to predict neural network performance for more efficient NAS.
problem Inaccurate performance metrics in NAS lead to suboptimal model designs.
method Proposes BRP-NAS, a hardware-aware NAS using GCNs for accurate performance prediction.
result BRP-NAS outperforms previous methods on NAS-Bench-101 and 201, improving model sample efficiency.
Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101, the first public arc…
YC Bench forecasts startup success in Y Combinator batches with a short-term metric.
problem Difficult forecasting of startup success due to sparse meaningful outcomes and slow evaluation cycles.
method Developed a live benchmark using publicly available traction signals and web visibility metrics.
result Revealed 6 out of 11 top performers at YC Demo Day with a simple proxy for prior brand recognition.
Look-Ahead-Bench evaluates financial LLMs for lookahead bias, revealing significant differences in model performance.
problem Measuring and mitigating lookahead bias in financial LLMs.
method Standardized benchmark evaluating model behavior in practical financial scenarios, analyzing performance decay across market regimes.
result Standard LLMs exhibit significant lookahead bias, while Pitinf models show improved generalization and reasoning abilities.
This study analyzes NAS benchmarks and finds that only a subset of operations is crucial for generating high-performing architectures.
problem NAS benchmarks lack generability and provide skewed performance distributions, leading to unreliable comparisons.
method Empirical analysis of widely used NAS benchmarks (101, 201, TransNAS-Bench-101) focusing on operation importance and generability.
result Only a subset of operations is necessary to generate architectures close to the upper-bound performance range, and convolution layers have the highest impact.
BIG-bench benchmarks language models, revealing their strengths and weaknesses.
problem Understanding and quantifying the capabilities of large language models.
method Developed the BIG-bench benchmark with 204 tasks from various domains, evaluated across multiple model sizes and types.
result Model performance improves with scale but remains poor, with breakthrough behaviors often involving multiple steps.
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.
One-shot neural architecture search (NAS) has played a crucial role in making NAS methods computationally feasible in practice. Nevertheless, there is still a lack of understanding on how these weight-sharing algorithms exactly work due to the many factors controlling the dynamics of the process. In order to allow a sc…
AutoWS-Bench-101 evaluates automated weak supervision methods for diverse domains.
problem Limited applicability of weak supervision due to difficulty in designing labeling functions.
method Automates labeling function design using a small set of ground truth labels.
result AutoWS methods often require foundation models to outperform simple few-shot baselines.
Benchmark evaluates financial misinformation detection models, revealing weaknesses without external context.
problem Detecting financial misinformation without external references.
method RFC Bench at paragraph level, two tasks: reference-free detection and comparison-based diagnosis.
result Performance improves with comparative context, revealing model weaknesses in reference-free settings.
Decision making from data involves identifying a set of attributes that contribute to effective decision making through computational intelligence. The presence of missing values greatly influences the selection of right set of attributes and this renders degradation in classification accuracies of the classifiers. As …
EDINET-Bench evaluates LLMs on complex financial tasks using Japanese financial statements.
problem Challenges in evaluating LLMs on financial tasks due to specialized expertise and scarce benchmarks.
method Developed EDINET-Bench, an open-source Japanese financial benchmark for LLMs on tasks like fraud detection and earnings forecasting.
result State-of-the-art LLMs perform only marginally better than logistic regression in financial tasks, highlighting the need for more realistic benchmarks.
The authors seek financial datasets to benchmark feature engineering methods on US market data.
problem Improving predictive models for financial data science competitions.
method Feature engineering methods applied to multivariate time-series data from the US market.
result Predictive power of models tested against Numerai-Signals targets.
Automates neural network design without training, speeding up search by seconds.
problem Time and effort in hand-designing deep neural networks.
method Predict trained accuracy from untrained network state using activation overlap.
result Search for powerful networks in seconds, verified on various benchmarks.
Hybrid framework injects TSLM insights into GRLM for robust time-series reasoning.
problem Lack of domain-specific knowledge in large language models for time-series reasoning.
method Hybrid knowledge-injection framework combining RLVR for efficient knowledge transfer.
result Consistently outperforms existing models by 7.9%-26.1% on multivariate time-series benchmarks.
XAI-Bench releases synthetic datasets for evaluating feature attribution methods.
problem Evaluating and comparing feature attribution methods is challenging.
method Released synthetic datasets and benchmarking library.
result Efficiently evaluates feature attribution methods across various metrics.
A new large-scale tabular benchmark for Learning from Label Proportions.
problem Lack of a large-scale open benchmark for tabular Learning from Label Proportions.
method Proposed LLP-Bench, a suite of 70 datasets (62 feature bag and 8 random bag) from real-world tabular data.
result Demonstrated the effectiveness of 9 SOTA and popular tabular LLP techniques on 62 feature bag datasets.
PredictionMarketBench benchmarks trading agents on prediction markets.
problem Evaluating trading agents on prediction markets with realistic conditions.
method Deterministic replay of historical data, execution-realistic simulator, agent interface.
result Fee-aware algorithmic strategies outperform naive agents in volatile episodes.
LLM4Causal democratizes causal reasoning via fine-tuned LLMs.
problem Limited capability of LLMs in causal inference and interpretation.
method Fine-tuning an open-source LLM for causal tasks, proposing datasets for instruction tuning.
result LLM4Causal delivers end-to-end solutions for causal problems and interprets results easily.
WeakNAS uses a set of weaker predictors to find top architectures with fewer samples.
problem Finding the best neural architecture with heavy computation costs.
method Proposes a paradigm shift from fitting the whole architecture space to progressively fitting a search path through a set of weaker predictors.
result WeakNAS produces coarse-to-fine iteration to gradually refine the ranking of sampling space, requiring fewer samples to find top-performance architectures.
Smooth embedding space improves NAS performance.
problem Efficiently predicting good neural architectures.
method Two-sided variational graph autoencoder.
result Smooth embedding space facilitates extrapolation to unseen architectures.
Dropping a tiny fraction of preferences can significantly alter the rankings of top LLMs.
problem Robustness of LLM ranking systems to small changes in preference data.
method A computational method based on the Bradley-Terry model to evaluate robustness.
result Top LLM rankings can be highly sensitive to the removal of a small fraction of preferences.
Probabilistic graphical models (PGMs) have become a popular tool for computational analysis of biological data in a variety of domains. But, what exactly are they and how do they work? How can we use PGMs to discover patterns that are biologically relevant? And to what extent can PGMs help us formulate new hypotheses t…
Generative diffusion models improve financial LOB simulation and forecasting.
problem High noise and complexity in financial LOB data makes deep generative models ineffective.
method Convert LOB data to images, apply diffusion models with inpainting for long-term sequence generation.
result Our method achieves state-of-the-art performance on LOB-Bench, improving coherence over local details.
Guided Evolution improves NAS efficiency and accuracy.
problem NAS methods converge to local minima and are complex.
method G-EA: guided evolutionary approach with initialization evaluation and continuous knowledge extraction.
result G-EA achieves state-of-the-art results in CIFAR-10, CIFAR-100, and ImageNet16-120.
Paper proposes FinAR-Bench to evaluate LLMs in financial analysis tasks.
problem Inaccurate financial analysis by LLMs leading to investment and regulatory issues.
method Proposes FinAR-Bench, a benchmark dataset with three steps: key info extraction, financial indicator calculation, and logical reasoning.
result LLMs perform better in key info extraction and indicator calculation but struggle with logical reasoning.
CFA improves model's ability to generalize across unseen domain-class combinations.
problem Challenges in real-world machine learning applications due to data distribution shifts and limited training data.
method Developed Compositional Feature Alignment (CFA) technique to improve CG ability of pretrained models.
result CFA outperforms common finetuning techniques in compositional generalization.
Chronos-2 forecasts multivariate and covariate data without task-specific training.
problem Limited applicability of existing time series forecasting models to real-world multivariate and covariate data.
method Chronos-2 uses a group attention mechanism for in-context learning across multiple time series.
result Chronos-2 achieves state-of-the-art performance across comprehensive benchmarks.
A method for a single policy to solve various tasks across diverse agent morphologies.
problem Generalizing a single policy to solve various tasks across diverse agent morphologies.
method Unified representation and behavior distillation using a morphology-task graph and Transformer architecture.
result Improves multi-task performances compared to baselines, suggesting a promising approach.
ADR helps LLMs find and use historical analogies for foresight analysis.
problem LLMs struggle to find relevant historical analogies due to surface-level matching.
method Proposes CANA framework with mechanism alignment and cross-analogy confirmation.
result CANA improves historical analogy generation by up to 10%.
Study explores calibration properties in neural architectures.
problem Calibration issues in deep neural networks despite improved accuracy.
method Leverages Neural Architecture Search (NAS) to evaluate 117,702 neural networks.
result Identifies key architectural designs beneficial for calibration.
SPIN converts weak LLMs to strong ones using self-play.
problem Growing strong LLMs without human-annotated data.
method Self-play fine-tuning (SPIN) starting from a supervised fine-tuned model.
result SPIN significantly improves LLM performance across benchmarks.
Neural Architecture Search remains a very challenging meta-learning problem. Several recent techniques based on parameter-sharing idea have focused on reducing the NAS running time by leveraging proxy models, leading to architectures with competitive performance compared to those with hand-crafted designs. In this pape…
URSABench benchmarks Bayesian methods for deep learning models.
problem Scalability issues in Bayesian inference for deep learning.
method Open-source benchmark suite for assessing approximate Bayesian inference methods.
result Initial results show promise for addressing uncertainty and robustness in deep learning.
PDO optimizes LLM prompts without labels, improving performance.
problem Optimizing prompts for LLMs without access to labeled data.
method Pairwise preference feedback, dueling bandits, Thompson Sampling, mutation.
result PDO identifies stronger prompts than label-free methods.
Parallel neural network training yields better long-term prediction accuracy.
problem Choosing the right training strategy for neural networks in dynamical systems.
method Comparison of parallel and series-parallel training strategies on five neural network architectures and two examples.
result Parallel training consistently outperforms series-parallel training in long-term prediction accuracy.
A new trading model combines GARCH and PPO for better stock trading profits.
problem Limited performance of reinforcement learning in stock market trading.
method Parallel-network continuous trading model using GARCH and PPO.
result The model achieves more profit compared to traditional reinforcement learning methods.
Improved active output selection reduces calibration time by 10% or more.
problem Efficiently calibrate models with noisy data.
method Improved active output selection strategy considering noise estimate.
result At least 10% fewer measurements needed compared to existing strategies.
Nowadays stochastic approximation methods are one of the major research direction to deal with the large-scale machine learning problems. From stochastic first order methods, now the focus is shifting to stochastic second order methods due to their faster convergence and availability of computing resources. In this pap…
This work benchmarks and theorizes robust NAS under adversarial training.
problem Lack of benchmark evaluations and theoretical guarantees for robust NAS architectures under adversarial training.
method Released a comprehensive data set and established a generalization theory using the neural tangent kernel.
result Established a generalization theory for robust NAS architectures under adversarial training.