The paper proposes a framework to detect student misconceptions from textual responses.
problem Detecting misconceptions from students' responses to open-response questions.
method A natural language processing-based probabilistic model for detecting common misconceptions.
result The proposed framework excels at classifying and detecting common misconceptions.
Corrected a misunderstanding about generalized Lie algebroids.
problem Misconception about generalized Lie algebroids.
method Proof
result Generalized Lie algebroids are not a valid geometric object.
Current XAI research lacks solid foundations and clear goals.
problem Inadequate conceptual, ethical, and methodological foundations in XAI research.
method Discussion of misconceptions and suggestions for improvement.
result Current XAI research needs to address conceptual, ethical, and methodological issues.
We call attention against what seems to a widely held misconception according to which large crashes are the largest events of distributions of price variations with fat tails. We demonstrate on the Dow Jones Industrial index that with high probability the three largest crashes in this century are outliers. This result…
The study corrects misconceptions in GBDT speed benchmarks.
problem Misleading speed benchmarks of GBDT algorithms.
method Explained and criticized several straightforward benchmarking methods, outlined fair benchmark requirements.
result A fair GBDT speed benchmark requires specific conditions.
Corrects the misconception that market impact is just volatility.
problem Misinterpretation of market impact as volatility.
method Introducing a simple scaling argument and comparing it to empirical data.
result Market impact is not related to price diffusion.
Theory vs practice in machine learning, showing practical limitations.
problem Applying machine learning theory to real-world business problems.
method Formalized and compared applied learning and agnostic PAC learning.
result Theoretical learning requires impractically large datasets.
Epicurus' philosophy aligns with Reinforcement Learning principles.
problem Misconceptions about Epicurean philosophy and its relation to RL.
method Analysis of Epicurus' letters and comparison with RL concepts.
result Epicurean hedonism objective function is equivalent to RL objective function.
New generalized Lie algebroids solve optimal control problems.
problem Optimal control problems not solvable by Lie algebroids.
method Proved generalized Lie algebroids as distinguished examples, disproved a theorem, and provided a new framework.
result Generalized Lie algebroids solve problems Lie algebroids cannot.
This paper compares two clustering evaluation metrics, revealing their differences and properties.
problem Understanding the differences between misclassification error distance and adjusted Rand index.
method Population origins, data analysis examples, detailed case studies, and simulation study.
result Reveals previous misconceptions about the two metrics and their distributions.
Novel approach embeds loss tunnels in neural networks, revealing insights into their structure.
problem Understanding the structure of neural network loss surfaces, especially low-loss tunnels.
method Directly embedding loss tunnels into the loss landscape of neural networks.
result Improved insights into the length and structure of loss tunnels, and better subspace inference in Bayesian neural networks.
The paper clarifies that embeddings can either reduce or maintain the dimensionality of sparse feature spaces.
problem Misconception about embedding dimensionality in sparse feature spaces.
method Analysis of information entropy and upper bounds for embedding dimensions.
result Embeddings can either reduce or maintain the dimensionality of sparse feature spaces, providing a meaningful representation.
Deep Curvature Suite offers a PyTorch package for neural network curvature analysis.
problem Insufficient use of curvature information in neural networks.
method Implementation of Lanczos algorithm for neural network curvature analysis.
result Our package outperforms existing methods for similar purposes.
The paper exposes common misconceptions about OOD detection and proposes a new framework.
problem Density-based OOD detection fails in deep learning settings.
method Proposes the OOD proxy framework to unify likelihood-ratio-based methods.
result Likelihood ratio is a principled method for OOD detection.
This work reformulates GAN training as variational inequalities to improve training stability.
problem Training GANs is difficult due to the saddle point optimization problem.
method Casts GAN optimization as variational inequalities and applies optimization techniques.
result Proposed techniques improve GAN training stability and sample quality.
LLMs struggle with financial reasoning but can outperform the market with human oversight.
problem Financial reasoning failures in LLM-generated stock market predictions.
method Evaluated four LLMs using three prompting strategies and compared to human oversight.
result LLMs require human oversight to fully realize their potential in financial markets.
This paper is about two related decision theoretic problems, nonparametric two-sample testing and independence testing. There is a belief that two recently proposed solutions, based on kernels and distances between pairs of points, behave well in high-dimensional settings. We identify different sources of misconception…
This paper examines linear embeddings for high-dimensional Bayesian optimization, identifying and addressing issues to improve performance.
problem Scaling Bayesian optimization to high-dimensional spaces while maintaining sample efficiency.
method Study and empirical evaluation of linear embeddings for BO, addressing design choices and their impact on performance.
result Properly addressing issues in linear embeddings significantly improves their efficacy in BO.
The Johansen-Ledoit-Sornette (JLS) model of rational expectation bubbles with finite-time singular crash hazard rates has been developed to describe the dynamics of financial bubbles and crashes. It has been applied successfully to a large variety of financial bubbles in many different markets. Having been developed fo…
A tutorial on VAEs explaining its derivation and applications.
problem Understanding the VAE model and its limitations.
method Explains VAE through probabilistic and information theoretic perspectives.
result Identifies two common misconceptions and their practical consequences.
A new acquisition function RMES improves Bayesian optimization performance.
problem Improper evaluation of mutual information in MES leads to suboptimal performance.
method Developed rectified MES (RMES) and used stochastic gradient ascent with reparameterization.
result RMES shows consistent improvement over MES in benchmarks and real-world problems.
Mathematical properties of the historical GDP/cap distributions are discussed and explained. These distributions are frequently incorrectly interpreted and the Unified Growth Theory is an outstanding example of such common misconceptions. It is shown here that the fundamental postulates of this theory are contradicted …
LLMs show potential for predicting financial returns, contrary to common belief.
problem Common belief that LLMs are unsuitable for financial market returns prediction.
method Chronos model from Ansari et al. (2024) tested on largest American single stocks.
result LLMs can predict time series that are nearly random, generating alpha.
1-Lipschitz networks are as accurate as classical networks and offer robustness.
problem Misconceptions about 1-Lipschitz neural networks and their properties.
method Analysis of 1-Lipschitz neural networks' accuracy, robustness, and generalization.
result 1-Lipschitz neural networks are as accurate as classical networks and can fit arbitrarily difficult boundaries.
Shampoo optimizes preconditioners for faster convergence in machine learning.
problem Improving convergence speed in machine learning optimization.
method Explicit connection between Shampoo's Kronecker product approximation and optimal matrix approximations.
result The square of Shampoo's approximation is equivalent to a single power iteration step for optimal Kronecker product approximation.
LoRA-One uses one-step full gradient to align adapters for efficient large model fine-tuning.
problem Fine-tuning large language models efficiently and accurately.
method Properly initializing LoRA adapters using the one-step full gradient and incorporating preconditioners.
result LoRA-One achieves significant empirical improvements over existing methods.
The study examines stock splits and their effects on companies, managers, and shareholders.
problem Misunderstandings and confounding factors around stock splits and their impacts.
method Selected database analysis of nine recent events, examining market impact, trading volume, and shareholder base.
result Stock splits enhance trading volume, increase shareholder base, and improve market liquidity.
This study surveys methods for detecting outliers in spatial data.
problem Detecting outliers in spatial data to avoid misinterpretation and enhance analysis.
method Survey of existing outlier detection methods for spatial data.
result Outliers in spatial data can be valuable if analyzed separately.
Research shows guidance in diffusion models does not sample from intended distribution, affecting boundary sampling.
problem Clarifying the misconception that guidance modifies the data distribution in diffusion models.
method Rigorous proof and fine-grained analysis of guidance dynamics in two cases: mixtures of compactly supported distributions and mixtures of Gaussians.
result Guidance leads to sampling more heavily from the boundary of the support of the conditional distribution as the parameter increases.
This paper explores Bayesian Neural Network posteriors, uncovering symmetries and their impact.
problem Understanding the complex posterior distribution of deep Bayesian Neural Networks.
method Investigates optimal approaches for approximating posteriors, analyzes modes, and explores visualizations.
result Uncovered weight-space symmetries and their impact on the posterior, particularly scaling symmetries.
Paper resolves apparent conflict between group and individual fairness.
problem Apparent conflict between group and individual fairness in machine learning.
method Theoretical discussions from fair machine learning, political, and legal philosophy.
result Individual and group fairness are not fundamentally in conflict.
Paper tackles zero-shot code feedback using rubric sampling with deep learning.
problem Lack of historical data for supervised learning in introductory programming assignments.
method Human-in-the-loop rubric sampling with deep learning inference.
result Autonomous feedback for first students is more accurate than data-hungry algorithms and approaches human level fidelity.
Laplace approximation improves deep learning efficiency without sacrificing performance.
problem Bayesian deep learning's practical implementation and efficiency.
method Review and implementation of Laplace approximation (LA) in PyTorch.
result Laplace approximation is competitive with popular alternatives in performance but significantly more efficient.
This paper analyzes liquidations in DeFi protocols, showing how price volatility can lead to significant losses.
problem Price volatility undermines overcollateralization in DeFi protocols, leading to potential losses.
method Empirical analysis of Compound's PLFs, examining participants' behavior and risk-appetite.
result Price volatility can result in over 10m USD becoming liquidable with only 3% price change.
Paper shows spectral filters can transfer between different graphs discretizing the same space.
problem Transferability of spectral filters between different graphs.
method Analysis of spectral filters on graphs discretizing the same space.
result Spectral filters have similar effects on graphs discretizing the same space.
BERT fine-tuning is unstable due to optimization issues, not forgetting or dataset size.
problem Stability of fine-tuning BERT-based models across different random seeds.
method Analysis of BERT, RoBERTa, and ALBERT fine-tuned on GLUE datasets, identifying optimization difficulties as the cause of instability.
result Fine-tuning instability is due to optimization difficulties leading to vanishing gradients, not forgetting or dataset size.
Paper proves spectral filters can be transferred between graphs.
problem Proving spectral filters can be transferred between graphs.
method Introducing the Cayley smoothness space and proving filters in this space are linearly stable.
result Graph spectral filters are transferable if they are in the Cayley smoothness space.
Paper formalizes anti-discrimination law in automated systems.
problem Algorithmic discrimination in legal contexts.
method Decision-theoretic framework grounded in UK anti-discrimination law.
result Introduced 'conditional estimation parity' metric for ML fairness.
This work improves independence tests for high-dimensional data.
problem Detecting subtle dependencies between high-dimensional random variables with complex distributions.
method Develops two approaches to learn powerful independence tests using variational mutual information and HSIC.
result Optimized HSIC tests generally outperform other approaches on detecting structured dependence.
New analysis shows Thompson Sampling can work with greedy approximations in combinatorial bandits.
problem Thompson Sampling's theoretical limits with greedy approximations in combinatorial semi-bandits.
method Study with greedy oracle, providing lower and upper bounds on regret.
result First theoretical results showing TS can work with greedy approximations, breaking misconceptions.
Study on trade-offs between accuracy and interpretability in machine learning.
problem Lack of formal study on statistical cost of interpretability.
method Modeling interpretability as a constraint in empirical risk minimization for binary classification.
result Explains conditions under which accuracy trade-off occurs with interpretability constraints.
New software package for scalable DPMM inference on large datasets.
problem Scalability and practical adoption of Dirichlet Process Mixture Models.
method Efficient distributed sampling-based inference on CPUs and GPUs.
result Significant speedups and fitting of larger datasets.