Machine learning research depends on objectively interpretable, comparable, and reproducible algorithm benchmarks. We advocate the use of curated, comprehensive suites of machine learning tasks to standardize the setup, execution, and reporting of benchmarks. We enable this through software tools that help to create an…
We propose iSCMs to standardize SCM data, improving causal inference.
problem Artifacts in SCM data can lead to misleading conclusions.
method We introduce internally-standardized structural causal models (iSCMs).
result iSCMs are not Var-sortable and mostly not R2-sortable. Neural network pruning lacks standardized benchmarks and metrics.
problem Lack of standardized benchmarks and metrics in neural network pruning.
method Meta-analysis of 81 papers, controlled conditions, ShrinkBench framework.
result Neural network pruning community lacks standardized benchmarks and metrics.
QuantBench benchmarks AI methods for quantitative investment.
problem Lack of a standardized benchmark for AI in quantitative investment.
method Developed an industrial-grade benchmark platform with standardization, flexibility, and full-pipeline coverage.
result Revealed critical research directions in AI for quantitative investment.
TUDataset provides benchmark datasets for graph learning.
problem Lack of meaningful benchmark datasets and standardized evaluation procedures for graph learning.
method Collection and standardization of 120 graph datasets from various applications.
result Standardized evaluation procedures and baseline experiments provided.
CleverHans is a software library that provides standardized reference implementations of adversarial example construction techniques and adversarial training. The library may be used to develop more robust machine learning models and to provide standardized benchmarks of models' performance in the adversarial setting. …
PerturBench benchmarks ML models for cellular perturbation analysis.
problem Standardizing benchmarking in modeling single cell transcriptomic responses to perturbations.
method Modular platform, diverse datasets, metrics, extensive evaluation, rank metrics.
result Simpler models are competitive and scale well with larger datasets.
Hybrid quantum-classical RL model solves standard benchmark tasks and proves quantum advantage.
problem Challenges in reinforcement learning, especially in solving standard benchmarking tasks.
method Parametrized quantum circuits in a hybrid quantum-classical RL model.
result Demonstrates quantum advantage in solving standard benchmarking tasks and intractable classical problems.
We present a comparative study of different probabilistic forecasting techniques on the task of predicting the electrical load of secondary substations and cabinets located in a low voltage distribution grid, as well as their aggregated power profile. The methods are evaluated using standard KPIs for deterministic and …
Machine learning (ML) needs industry-standard performance benchmarks to support design and competitive evaluation of the many emerging software and hardware solutions for ML. But ML training presents three unique benchmarking challenges absent from other domains: optimizations that improve training throughput can incre…
Revisits PPO design choices, exposing failure modes and proposing alternatives.
problem Failure modes of standard PPO in new environments.
method Revisits standard PPO design choices, exposes failure modes, and proposes alternative approaches.
result Alternative design choices prevent failure modes in new environments.
learn2learn simplifies meta-learning research by providing a library and standardized interfaces.
problem Prototyping and reproducibility issues in meta-learning.
method Developed a library (learn2learn) with common routines and standardized interfaces.
result Fosters a community around standardized software for meta-learning research.
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.
In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Then we propose a new dataset called ImageNet-P which enables researc…
New IRT method identifies useful datasets for ML classifier evaluation.
problem Lack of standard evaluation strategy for ML benchmarks.
method Applied Item Response Theory (IRT) to OpenML-CC18 benchmark.
result Not all datasets are useful for evaluating classifiers.
Tree-based models outperform deep learning on tabular data, especially for medium-sized datasets.
problem Understanding why tree-based models outperform deep learning on tabular data.
method Extensive benchmarks of tree-based and deep learning models on 45 datasets, accounting for hyperparameters.
result Tree-based models remain state-of-the-art on medium-sized tabular data, even without hyperparameter optimization.
New benchmarks focus on LLM risk in finance, not just accuracy.
problem Standard benchmarks ignore LLM financial risks, leading to unsafe deployment.
method Three-level agenda: model, workflow, and system stress-testing.
result Hidden weaknesses in LLMs are missed by traditional benchmarks.
WRENCH benchmarks weak supervision datasets for machine learning.
problem Lack of standardized evaluation for weak supervision datasets.
method Developed a comprehensive benchmark platform WRENCH.
result Demonstrated the efficacy of WRENCH as a benchmark platform.
Unified benchmarks assess data poisoning and backdoor attacks.
problem Unclear danger and effectiveness of data poisoning methods.
method Developed standardized benchmarks for data poisoning and backdoor attacks.
result Existing methods may not generalize to realistic settings.
Paper proposes a new daily benchmark for post-GFC government bond CIP deviations.
problem Lack of a canonical daily benchmark for CIP deviations.
method Used G10 plus KRW currency-tenor panels to analyze three lagged public state variables.
result Three lagged public state variables deliver strong performance in daily regressions.
Study proposes new methods to calculate probabilistic benchmarks in noisy data.
problem Identifying opportunities for improvement in comparable units with noisy data.
method 2-step methodology involving undersampling and relevance vector machine.
result Higher discrimination power achieved with macro-economic environment variables.
This paper predicts weekly stock market movements using machine learning and introduces a new benchmark.
problem Predicting stock market movements using daily data and various ML models.
method Focuses on weekly movements, introduces random traders as a benchmark, uses additional features, and adjusts training datasets.
result Trained models, especially MLP, show good performance across different trends.
Paper introduces a fraud detection dataset benchmark.
problem Unique challenges in fraud detection datasets.
method Compilation of publicly available fraud datasets.
result Demonstrates applications of the Fraud Dataset Benchmark.
We present a formulation of the transaction cost analysis (TCA) in the Bayesian framework for the primary purpose of comparing broker algorithms using standardized benchmarks. Our formulation allows effective calculation of the expected value of trading benchmarks with only a finite sample of data relevant to practical…
BAT benchmark for autobidding tasks in RTB auctions.
problem Lack of comprehensive datasets and benchmarks for autobidding.
method Developed a benchmark for two auction formats, implemented robust baselines.
result Provides a framework for developing and refining autobidding algorithms.
Simulated DAGs can mislead structure learning algorithms due to variance patterns.
problem Structure learning algorithms can be misled by variance patterns in simulated DAG models.
method Introduced varsortability as a measure of agreement between marginal variance order and causal order.
result Performance of structure learning algorithms can be explained by high varsortability, but this does not generalize to real-world data.
Variational approaches based on neural networks are showing promise for estimating mutual information (MI) between high dimensional variables. However, they can be difficult to use in practice due to poorly understood bias/variance tradeoffs. We theoretically show that, under some conditions, estimators such as MINE ex…
The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving. We here provide an easy-to-use benchmark to assess how object detection models perform when image quality degrades. The three resulting benchmark datasets,…
New benchmarks for RNA 3D structure-function modeling.
problem Lack of standardized benchmarks for RNA deep learning.
method Developed seven benchmark datasets, provided tools for data handling, and offered a user-friendly environment for model comparison.
result Demonstrated utility with baseline results using a relational graph neural network.
BREEDS benchmarks assess model robustness to subpopulation shifts.
problem Measuring model robustness to novel subpopulation shifts.
method Controlled synthesis of realistic distribution shifts using class structure.
result Validated model sensitivity and effectiveness of robustness interventions.
High-dimensional shrinkage risk depends on the default prior for the common scale.
problem Choosing the default prior for the common scale in high-dimensional shrinkage.
method Using radial-power benchmark to compare variance-flat and standard deviation-flat priors.
result The standard deviation-flat prior has a one-unit asymptotic risk advantage near the origin.
Bounds on long-term returns of leveraged ETFs are given.
problem Uncertainty in long-term returns of leveraged ETFs.
method Quadratic bounds on log-returns based on daily log-returns of the underlying index.
result Sufficient conditions for outperformance and underperformance of leveraged ETFs.
The study compares M6 competitors' performance to industry benchmarks and discusses incentives for investment managers.
problem Investors seek to understand the performance and skill of M6 competitors beyond the competition's metrics.
method Comparative analysis using financial metrics, factor models, and new strategies.
result Most competitors do not generate significant out-performance compared to industry benchmarks, but some show skill in recent performance.
This paper benchmarks algorithms for training fair DNNs, addressing real-world fairness constraints.
problem Training deep neural networks with fairness constraints.
method Benchmarking stochastic approximation algorithms for fairness-constrained DNN training.
result Demonstrates the use of a new benchmark for comparing fairness-improving algorithms.
In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Unlike recent robustness research, this benchmark evaluates performan…
GraphBench creates a unified benchmark for graph learning tasks.
problem Fragmented benchmarking practices and inconsistent evaluation protocols in graph learning.
method Developed a comprehensive benchmark suite with standardized evaluation protocols.
result Established principled baselines for future research in graph learning.
Agent57 beats human average on all Atari games.
problem Atari game benchmark's poor performance in challenging games.
method Trained neural network with adaptive policy selection and novel architecture.
result First deep RL agent to outperform human average on all 57 Atari games.
We offer an experimental benchmark and empirical study for off-policy policy evaluation (OPE) in reinforcement learning, which is a key problem in many safety critical applications. Given the increasing interest in deploying learning-based methods, there has been a flurry of recent proposals for OPE method, leading to …
FEET protocol evaluates foundation models across three scenarios.
problem Lack of standardized evaluation protocols for foundation models.
method Structured evaluation protocol across three use cases: frozen, few-shot, and fine-tuned embeddings.
result Demonstrates comprehensive assessment of foundation models' effectiveness.
Randomly guessing weights helps analyze RL benchmarks objectively.
problem Understanding the complexity of reinforcement learning benchmarks.
method Generate policy networks by randomly guessing their parameters, evaluate on benchmarks, and analyze results.
result Small untrained networks can provide a robust baseline for various RL tasks.
We study inference and learning based on a sparse coding model with `spike-and-slab' prior. As in standard sparse coding, the model used assumes independent latent sources that linearly combine to generate data points. However, instead of using a standard sparse prior such as a Laplace distribution, we study the applic…
Language model benchmarks often misrepresent true understanding, revealing vulnerabilities in evaluation methods.
problem Language model benchmarks fail to accurately reflect true language understanding and adaptability.
method Systematic analysis of NLP evaluation frameworks, identifying vulnerabilities in static benchmarks, human evaluation protocols, and LLM-as-judge frameworks.
result Current evaluation methods are unreliable and need improvement to accurately assess LLM performance.
TailedTS dataset benchmarks heavy-tailed time series forecasting and periodicity quantification.
problem Benchmarking robustness of time series models under heavy-tailed distributions.
method Derived from Wikipedia page views, introduces periodicity quantification and robust loss functions.
result Standard Gaussian models degrade on high-volume page categories, while robust alternatives perform consistently.
RobustBench aims to standardize adversarial robustness evaluation in image classification.
problem Lack of systematic understanding and error-prone robustness evaluations.
method Standardized benchmark with restricted models and adaptive attacks.
result Reflects current state of the art in adversarial robustness.
Combines absolute and relative wealth in portfolio optimization with power utility functions.
problem Optimizing portfolios with both absolute and relative wealth considerations.
method Integrates power utility functions for absolute and relative wealth, considering multiple benchmarks.
result Obtains an explicit solution for portfolio optimization combining absolute and relative wealth.
We use surrogate losses to obtain several new regret bounds and new algorithms for contextual bandit learning. Using the ramp loss, we derive new margin-based regret bounds in terms of standard sequential complexity measures of a benchmark class of real-valued regression functions. Using the hinge loss, we derive an ef…
We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations. Our model stacks multiple latent GP layers to learn abstract representations of the state feature space, which is link…
Minimax linkage was first introduced by Ao et al. [3] in 2004, as an alternative to standard linkage methods used in hierarchical clustering. Minimax linkage relies on distances to a prototype for each cluster; this prototype can be thought of as a representative object in the cluster, hence improving the interpretabil…