New algorithms for n-player games using a player-centered approach.
problem Learning near-perfect strategies in multiplayer games.
method Player-centered reinforcement learning with Final Adaptation RL.
result FARL is crucial for achieving near-perfect strategies in various games.
New optimization method helps models generalize better after achieving near-perfect training performance.
problem Models can achieve near-perfect training performance but fail to generalize well to unseen examples.
method GROKtimizer combines rapid convergence to interpolation with post-interpolation norm minimization using Critically Damped Momentum.
result GROKtimizer provides a quadratic speedup over classical gradient descent, offering a natural solution for selecting low-norm interpolating solutions.
High-dimensional spectroscopy data makes ML models achieve near-perfect accuracy, even when chemical distinctions are absent.
problem Why machine learning models achieve near-perfect accuracy in spectroscopic classification tasks without chemically meaningful features.
method Theoretical analysis grounded in the Feldman-Hajek theorem and concentration of measure, combined with specific experiments on synthetic and real fluorescence spectra.
result Infinitesimal distributional differences in high-dimensional spaces can lead to perfect separability, making models achieve near-perfect accuracy in spectroscopy.
Resource scheduling and coordination is an NP-hard optimization requiring an efficient allocation of agents to a set of tasks with upper- and lower bound temporal and resource constraints. Due to the large-scale and dynamic nature of resource coordination in hospitals and factories, human domain experts manually plan a…
Artificial neural networks (ANNs) have gained a well-deserved popularity among machine learning tools upon their recent successful applications in image- and sound processing and classification problems. ANNs have also been applied for predicting the family or function of a protein, knowing its residue sequence. Here w…
New insights into image compression trade-offs with private randomness.
problem Trade-off between compression rate and perceptual quality in image compression.
method Characterization of rate-distortion trade-off with private randomness under different realism constraints.
result Encoder private randomness is not useful if compression rate is below source entropy, even with limited common and decoder private randomness.
Study optimal auction formats for maximizing MEV on Ethereum.
problem Maximizing extractable value from Ethereum auctions.
method Empirical analysis of 2.2 million transactions, modeling affiliation among bidders.
result English and second-price sealed-bid auctions dominate other formats, with significant revenue losses.
Analyzes multi-day stock returns, showing linear volatility and mean dependence.
problem Linear dependence of volatility and mean in accumulated stock returns.
method Modified Jones-Faddy skew t-distribution analysis.
result Linear dependence of volatility and mean on the number of days of accumulation.
Graph neural networks struggle with structural noise.
problem Robustness of graph neural networks to structural noise.
method Controlled experiments with a representative GNN model.
result Graph neural networks are not robust to structural noise.
FLOP algorithm speeds up causal structure learning for linear models.
problem Efficiently learning causal structures from discrete data.
method FLOP algorithm combines fast parent selection and iterative score updates.
result FLOP finds highly accurate causal structures with near-perfect recovery.
Study explains how noisyGD with DP improves feature learning despite high dimensionality.
problem Improving feature learning in differential privacy settings with noisyGD.
method Layer-peeled model in representation learning, error bound analysis, feature normalization, PCA.
result Misclassification error is independent of dimension in NC, and PCA improves testing accuracy.
Interior tomography for the region-of-interest (ROI) imaging has advantages of using a small detector and reducing X-ray radiation dose. However, standard analytic reconstruction suffers from severe cupping artifacts due to existence of null space in the truncated Radon transform. Existing penalized reconstruction meth…
Study assesses consistency and reproducibility of LLMs in finance and accounting tasks.
problem Consistency and reproducibility of LLM outputs in finance and accounting research.
method Extensive experimentation with 50 independent runs across 5 tasks using 3 OpenAI models.
result Task-specific patterns of consistency and reproducibility, with binary classification and sentiment analysis achieving near-perfect reproducibility.
SVD-RND detects blurred images better than conventional methods.
problem Blurred images can fool conventional OOD detection schemes.
method Constructs a novel RND-based detector that uses blurred images during training.
result SVD-RND outperforms baseline detectors in various domains.
Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversari…
Measuring the morphological parameters of galaxies is a key requirement for studying their formation and evolution. Surveys such as the Sloan Digital Sky Survey (SDSS) have resulted in the availability of very large collections of images, which have permitted population-wide analyses of galaxy morphology. Morphological…
The paper explores grokking in various models, revealing it's not limited to neural networks.
problem Understanding grokking in different models and its mechanism.
method Empirical exploration of grokking in neural networks, Gaussian processes, linear regression, and Bayesian neural networks. Inducing grokking through spurious dimensions.
result Grokking occurs in non-neural architectures, indicating it's not model-specific.
Method calibrates basket options using rearranged samples from constituent processes.
problem Calibrate basket options with non-linear dependency structure.
method Propose a method to extract dependency structure from market data through systematic sampling rearrangement, then calibrate a local volatility model.
result Efficiently calibrates basket options with near-perfect accuracy.
We prove, under two sufficient conditions, that idealised models can have no adversarial examples. We discuss which idealised models satisfy our conditions, and show that idealised Bayesian neural networks (BNNs) satisfy these. We continue by studying near-idealised BNNs using HMC inference, demonstrating the theoretic…
A novel model-selection method for dynamic networks using synthetic data.
problem Classifying and understanding the growth mechanisms of dynamic networks.
method Training a classifier on synthetic network data generated by nine random graph models, using dynamic features that count new links.
result Achieves near-perfect classification of synthetic networks, outperforming state-of-the-art methods.
When the linear measurements of an instance of low-rank matrix recovery satisfy a restricted isometry property (RIP)---i.e. they are approximately norm-preserving---the problem is known to contain no spurious local minima, so exact recovery is guaranteed. In this paper, we show that moderate RIP is not enough to elimin…
The paper evaluates various machine learning models for predicting industrial aging processes.
problem Accurately predicting industrial aging processes to schedule maintenance efficiently.
method Compared traditional stateless models (linear and kernel ridge regression, feed-forward neural networks) to more complex recurrent neural networks (echo state networks and LSTMs) on synthetic and real-world data.
result Recurrent models produce near perfect predictions when trained on larger datasets and maintain good performance even with domain shifts, while simpler models perform comparably on smaller datasets.
FCA improves fair clustering by optimizing utility and fairness.
problem Balancing fairness and utility in clustering.
method FCA alternates between aligning data and optimizing cluster centers in an aligned space.
result FCA achieves a superior trade-off between fairness and utility.
Accumulated stock returns exhibit tempered skew t-distribution.
problem Analyzing the distribution of stock returns over multiple days.
method Employing a tempered skew t-distribution model.
result Tempered skew t-distribution fits the distribution of accumulated stock returns well.
New method encodes function preferences into neural nets for better generalization.
problem Challenges in encoding explicit function preferences in neural network training.
method Function-space empirical Bayes (FSEB) regularization.
result FSEB leads to near-perfect semantic shift detection and improved generalization.
Machine learning confound removal biases results, leading to misleading predictions.
problem Common confound removal methods in machine learning lead to misleading predictions.
method Featurewise removal of confound variance by linear regression before applying ML.
result This common deconfounding approach can leak information, amplifying null or moderate effects.
Deep Reinforcement Learning (deep RL) has made several breakthroughs in recent years in applications ranging from complex control tasks in unmanned vehicles to game playing. Despite their success, deep RL still lacks several important capacities of human intelligence, such as transfer learning, abstraction and interpre…
New method turns any regression model into a calibrated probabilistic model.
problem Calibration and sharpness of uncertainty estimates in regression models.
method Modular Conformal Calibration (MCC) framework.
result MCC algorithms achieve near-perfect calibration and improved sharpness.
We present a stochastic agent-based model for the distribution of personal incomes in a developing economy. We start with the assumption that incomes are determined both by individual labour and by stochastic effects of trading and investment. The income from personal effort alone is distributed about a mean, while the…
Over-parameterized models can memorize noisy labels and still generalize well, revealing a hidden structure.
problem Understanding how over-parameterized models can simultaneously memorize noisy labels and generalize well.
method Investigated through modular arithmetic tasks with label noise using two-layer neural networks.
result Over-parameterized models can achieve near-perfect test accuracy with 80% label noise by extracting an internal generalization structure.
Paper proposes GrokTransfer to eliminate delayed generalization in neural networks.
problem Delayed generalization in neural networks, compromising predictability and efficiency.
method Trains a smaller, weaker model to reach a nontrivial test performance, then uses its learned input embedding to initialize the stronger model.
result GrokTransfer enables the target model to generalize directly without delay, across various tasks.
C-FAR automates clustering assessment for neural tracking.
problem Manual assessment of clusters by humans is slow and impractical for large datasets.
method C-FAR uses automated feedback queries to select optimal clustering from multiple algorithms.
result C-FAR produces near-perfect clustering on simulated neural data.
Study shows over-sampling biases prediction results on imbalanced datasets.
problem Over-optimistic prediction results on imbalanced data.
method Applying over-sampling before partitioning training and testing sets.
result Over-sampling causes biased results and reduces predictive performance.
LoRA and privacy: Random projections help but not always.
problem Ensuring differential privacy in LoRA fine-tuning.
method Wishart projection mechanism and noisy variants.
result LoRA is not inherently private, but low-rank fine-tuning can be more private.
Geometric stability predicts steerability and detects drift in language models.
problem Predicting steerability and detecting drift in language models.
method Supervised and unsupervised geometric stability measures.
result Supervised geometric stability predicts steerability with high accuracy and detects drift earlier.
Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query interfaces. ML-as-a-service ("predictive analytics") systems are an example: Some …
Improves consistency of weighted averaging estimators in active learning.
problem Consistency issues in weighted averaging estimators under active learning.
method Enforces random sampling through an augmented active learning algorithm.
result Generalizes Stone's Theorem for consistency of estimators under active learning.
EUREKA builds classifiers that use surprising features.
problem Building classifiers that are interesting, not just accurate.
method Uses large language models to rank features by interestingness and builds interpretable classifiers using only selected features.
result EUREKA discovers non-obvious yet predictive features, improving accuracy and offering insights.
Dropout schedules can be optimized to significantly reduce model test loss.
problem Improving model performance in neural networks.
method Developed a mean-field theory of dropout at the edge of chaos, proposing front-loaded dropout schedules.
result Front-loaded dropout schedules reduce test loss by 18-35% over constant dropout.
FinAI-BERT classifies AI disclosures in financial reports with high accuracy.
problem Systematic detection of AI-related disclosures in financial reports.
method Fine-tuned transformer-based model on a curated dataset.
result Achieved near-perfect classification performance (99.37% accuracy).
LLMs fail to match statistical ground truth despite stable run-to-run performance.
problem LLMs lack validation against statistical ground truth in automated scientific workflows.
method Introduced a behavioral evaluation framework for LLMs, separating four decision-making dimensions.
result LLMs can exhibit near-perfect stability but diverge from statistical ground truth.
Neural networks struggle with long sequences, but a new method improves their performance.
problem Neural networks struggle to generalize to longer sequences and unseen data.
method Proposed a learned conditional masking mechanism and binary encoding for numbers.
result Models can now generalize far outside their training range with near-perfect accuracy.
Developing classification algorithms that are fair with respect to sensitive attributes of the data has become an important problem due to the growing deployment of classification algorithms in various social contexts. Several recent works have focused on fairness with respect to a specific metric, modeled the correspo…
Improved selection of best outputs from LLMs for better accuracy.
problem BoN fails to reliably find the correct answer with imperfect rewards.
method Majority-of-the-Bests (MoB) selects the mode of a bootstrapped output distribution of BoN.
result MoB consistently improves over BoN in 25 out of 30 setups.
DECAT framework evaluates multimodal models for shared biology, detecting confounders and false positives.
problem Determining if multimodal models learn shared biology or just confounders.
method DECAT framework classifies multimodal representations into four diagnostic scenarios using null-referenced metrics.
result DECAT detects confounders and false positives in multimodal models, improving with larger cohorts and stronger representations.
Study identifies a Strategic Gap in market efficiency due to AI-driven timing and complexity in disclosure.
problem Market inefficiency due to structural influence of disclosure timing and complexity.
method Introduces Autonomous Disclosure Regulator, a multi-node AI framework to audit disclosure complexity and unpredictability.
result Companies use confusing language and unpredictable timing to slow down market learning, creating a 60% Structural Gap.
Contradistinguisher learns to distinguish target domain without aligning source and target domains.
problem Difficulty in aligning source and target domains for domain adaptation.
method Direct approach to unsupervised domain adaptation that learns contrastive features and improves classification performance.
result Achieves state-of-the-art performance on Office-31 and VisDA-2017 datasets.
TabSODA improves imputation of surveys with skips and ordinal data.
problem Handling structural skips and ordinal responses in survey data.
method TabSODA uses an Elucidated Diffusion Model with skip pattern detection and ordinal awareness.
result TabSODA reduces ordinal missing-at-random (MACE) by up to 23.7% and improves categorical accuracy by up to 9%.