Deep learning models accurately recognize and estimate physical activity types and energy expenditure from wrist accelerometer data.
problem Rigorous evaluation of wrist-worn accelerometers for assessing physical activity across the lifespan.
method Built deep learning networks to extract spatial and temporal representations from time-series data, recognizing physical activity types and estimating energy expenditure.
result Deep learning models achieved high performance: F1 scores of 0.82, 0.81, and 95 for sedentary, locomotor, and lifestyle activities, respectively; root mean square error of 1.1 for EE estimation.
The study analyzes optimization trajectories in neural networks to reveal redundancy and redundancy-reducing strategies.
problem Understanding the directional structure and redundancy in neural network optimization.
method Introducing natural notions of complexity for optimization trajectories and analyzing their directional nature.
result Training only scalar batchnorm parameters can match the performance of training the entire network, indicating potential for hybrid optimization schemes.
New bounds show empirical EOT adapts to simpler measure.
problem Statistical performance of empirical EOT estimators.
method Novel statistical bounds, empirical process theory, dual formulation.
result Empirical EOT and its unregularized version follow lower complexity adaptation.
Graph neural networks struggle to distinguish certain graph structures.
problem Difficulty in distinguishing graphs with graph neural networks.
method Analysis of communication capacity in message-passing model of graph neural networks.
result Capacity of MPNN needs to grow linearly for trees and quadratically for general connected graphs.
Measuring systemic risk or fragility of financial systems is a ubiquitous task of fundamental importance in analyzing market efficiency, portfolio allocation, and containment of financial contagions. Recent attempts have shown that representing such systems as a weighted graph characterizing the complex web of interact…
This paper introduces intrinsic time, a new measure of time for complex systems.
problem Traditional time measures fail to capture the dynamic nature of real-world phenomena.
method Intrinsic time uses an event-based, algorithmic framework to analyze time series data.
result Intrinsic time reveals novel structures and regularities in financial markets.
In this work, the time chart of Dow Jones Industrial Average (DJIA) index is analyzed and approach of recession time term is predicted, which may be hallmark of a worldwide economic crisis. However, the methods used for the prediction will be disclosed a few years from now. On the other hand, this work will be updated …
Quantum circuits predict volatility dynamics preserving asymmetry.
problem Modeling volatility time series with asymmetry.
method Single-qubit quantum circuit learning (QCL) applied to synthetic data generated by Rational GARCH model.
result QCL-based predictions preserve negative return-volatility correlation and anti-persistent behavior.
Survey revisits Bachelier and Dupire, highlighting optimal transport's role.
problem Finding arbitrage-free models calibrated to volatility surfaces.
method Revisits mathematical finance principles, uses optimal transport results.
result Optimal transport provides rigorous foundations for Dupire's model.
Develops a machine learning method for parameter estimation in branching processes models.
problem Parameter evaluation for unevenly distributed sparse and dense regions in stochastic datasets.
method Approximate Bayesian computation based on Isolation Kernel mapping and maxima weighted kernel.
result Effective parameter estimation for cancer cell evolution models using personal data.
Based on 1-minute price changes recorded since year 2012, the fluctuation properties of the rapidly-emerging Bitcoin (BTC) market are assessed over chosen sub-periods, in terms of return distributions, volatility autocorrelation, Hurst exponents and multiscaling effects. The findings are compared to the stylized facts …
Machine and reinforcement learning (RL) are increasingly being applied to plan and control the behavior of autonomous systems interacting with the physical world. Examples include self-driving vehicles, distributed sensor networks, and agile robots. However, when machine learning is to be applied in these new settings,…
Symmetry in finance is a neglected but potentially valuable concept.
problem The underutilization of symmetry in financial markets.
method Examining symmetry in game theory, technical analysis, and long-term economic growth.
result Symmetry principles can be applied to financial strategies and market dynamics.
Novel approach combines local and global brain changes for AD prediction.
problem Detecting Alzheimer's disease through local and global brain changes.
method Patch-based 3D-CNNs combined with global topological features for multi-scale brain tissue connectivity.
result Average precision score of 0.95 for classifying cognitively normal subjects and AD patients (prevalence ~55%).
Invariances to translation, rotation and other spatial transformations are a hallmark of the laws of motion, and have widespread use in the natural sciences to reduce the dimensionality of systems of equations. In supervised learning, such as in image classification tasks, rotation, translation and scale invariances ar…
Paper explores privacy in machine learning models using ICL.
problem Privacy in in-context learning models.
method Differentially private pretraining algorithm for linear attention heads.
result Characterizes privacy-accuracy trade-off for ICL in linear regression.
A central challenge of adversarial learning is to interpret the resulting hardened model. In this contribution, we ask how robust generalization can be visually discerned and whether a concise view of the interactions between a hardened decision map and input samples is possible. We first provide a means of visually co…
We establish conditions for compositional generalization in machine learning.
problem Achieving compositional generalization in machine learning models.
method We reformulate compositionality as a property of the data-generating process and derive mild conditions on the training distribution and model architecture.
result Our theoretical framework enables compositional generalization under mild conditions.
The paper tackles video prediction by estimating conditional densities implicitly.
problem Temporal prediction uncertainty and high-dimensional probabilistic inference in natural scenes.
method Score-based conditional density estimation using sequence-to-image networks trained on a resilience-to-noise objective.
result The method handles occlusion boundaries and weights predictive evidence by reliability.
GES algorithm improves consistency for nonparametric DAG models.
problem Consistent estimation of nonparametric DAG models.
method Greedy equivalence search with new consistency proof for nonparametric families.
result Consistency of GES for general nonparametric DAG models with smooth factorization.
A new approach combines prior knowledge with learning to adapt quickly to new tasks.
problem Adapting quickly to new tasks using prior knowledge.
method Combines behavior prior, robust off-policy learning, and value function representation.
result Achieves competitive adaptation performance compared to meta reinforcement learning baselines.
Framework for lifelong learning of compositional structures.
problem Learning to reuse self-contained chunks of knowledge for novel problems.
method Separates learning into combining existing components and adapting them.
result Framework handles trade-off between stability and flexibility.
Deep learning is attracting significant interest in the neuroimaging community as a means to diagnose psychiatric and neurological disorders from structural magnetic resonance images. However, there is a tendency amongst researchers to adopt architectures optimized for traditional computer vision tasks, rather than des…
Preserving the privacy of individuals by protecting their sensitive attributes is an important consideration during microdata release. However, it is equally important to preserve the quality or utility of the data for at least some targeted workloads. We propose a novel framework for privacy preservation based on the …
The paper challenges the use of decision trees for pointwise inference due to slow convergence rates.
problem The slow convergence rates of decision trees in uniform norm, especially with non-vanishing probability.
method Demonstrates the limitations of adaptive recursive partitioning and shows how random forests can improve performance.
result Decision trees can fail to achieve polynomial rates of convergence in uniform norm, even with pruning.
New embeddings capture local structure in complex networks.
problem Embeddings cannot capture local structure in complex networks.
method Logistic Principal Component Analysis (LPCA) algorithm for exact low-rank representations.
result Exact low-rank representations of real-world networks are possible.
Background: Fluctuating hearing loss is characteristic of Meniere's Disease (MD) during acute episodes. However, no reliable audiometric hallmarks are available for counselling the hearing recovery possibility. Aims/Objectives: To find parameters for predicting MD hearing outcomes. Material and Methods: We applied mach…
This paper explains how to optimize prompts for model adaptation.
problem Understanding and optimizing prompt tuning for model adaptation.
method Bayesian view and meta-learning to explain prompt optimization.
result Optimal prompting can be studied formally as conditioning Bayesian predictors.
Study challenges neural models in compositional learning tasks.
problem Challenges in neural models for compositional and relational learning.
method Introduced ConceptWorld environment for generating images from compositional concepts, tested various neural architectures.
result Neural models struggle with longer compositional chains and substitutivity tests.
HAL learns hierarchical affordances to prune impossible subtasks, improving reinforcement learning efficiency.
problem Reinforcement learning struggles with complex hierarchical dependency structures.
method HAL learns a model of hierarchical affordances to prune impossible subtasks.
result HAL agents are better at learning complex tasks, navigating stochastic environments, and acquiring diverse skills.
Despite significant recent progress, machine vision systems lag considerably behind their biological counterparts in performance, scalability, and robustness. A distinctive hallmark of the brain is its ability to automatically discover and model objects, at multiscale resolutions, from repeated exposures to unlabeled c…
New method automates asymmetric choice for better skill transfer in reinforcement learning.
problem Improving sample efficiency and transferability of reinforcement learning agents.
method Attentive Priors for Expressive and Transferable Skills (APES) using hierarchical KL-regularization.
result APES automates asymmetric choice, leading to better skill transfer across sequential tasks.
Hybrid pipeline detects spike-and-wave discharges in long-term EEG recordings.
problem Manual identification of spike-and-wave discharges in long-term EEG recordings is labour-intensive and error-prone.
method A hybrid pipeline that combines analytical features with a shallow ANN for SWD detection.
result The method correctly detected 384 out of 392 annotated SWD events, achieving high sensitivity and specificity.
Humans and animals show remarkable flexibility in adjusting their behaviour when their goals, or rewards in the environment change. While such flexibility is a hallmark of intelligent behaviour, these multi-task scenarios remain an important challenge for machine learning algorithms and neurobiological models alike. We…
Hybrid regularization avoids double descent in random feature models.
problem Avoiding the double descent phenomenon in random feature models.
method Combines early stopping and weight decay, using GCV for hyperparameter selection.
result Hybrid method successfully avoids double descent and achieves comparable generalization.
Combines pseudo-point and state space approximations for scalable GPs.
problem Handling large numbers of off-the-grid spatial data-points and long time-series.
method Combines pseudo-point approximations for spatial data with state space GP approximations for temporal data.
result Combined approach is more scalable and applicable to a greater range of spatio-temporal problems.
Study confirms financial bubbles' common patterns in isolated markets.
problem Testing universal dynamics of financial bubbles in isolated markets.
method Log-Periodic Power Law Singularity (LPPLS) model analysis of two major bubble episodes.
result Tehran Stock Exchange shows clear LPPLS hallmarks, supporting bubble universality.
Cross-correlations in fluctuations of the daily exchange rates within the basket of the 100 highest-capitalization cryptocurrencies over the period October 1, 2015, through March 31, 2019, are studied. The corresponding dynamics predominantly involve one leading eigenvalue of the correlation matrix, while the others la…
Industry-scale recommendation systems have become a cornerstone of the e-commerce shopping experience. For Etsy, an online marketplace with over 50 million handmade and vintage items, users come to rely on personalized recommendations to surface relevant items from its massive inventory. One hallmark of Etsy's shopping…
New VAE models reveal hierarchical visual cortex computations.
problem Capturing hierarchical visual cortex computations in generative models.
method Sparse coding hierarchical VAEs trained on natural images with varied generative and recognition components.
result Representations similar to those in visual cortex emerge under inductive biases.
Prototypical examples that best summarizes and compactly represents an underlying complex data distribution communicate meaningful insights to humans in domains where simple explanations are hard to extract. In this paper we present algorithms with strong theoretical guarantees to mine these data sets and select protot…
New benchmark PVR tests neural network reasoning about indirection.
problem Understanding neural network generalization limits.
method Introducing Pointer Value Retrieval (PVR) benchmark.
result Large variations in performance across different conditions.
Zero-sum games have long guided artificial intelligence research, since they possess both a rich strategy space of best-responses and a clear evaluation metric. What's more, competition is a vital mechanism in many real-world multi-agent systems capable of generating intelligent innovations: Darwinian evolution, the ma…
New method shows fully-connected networks can learn convolutional structures from data.
problem How to learn convolutional structures from translation-invariant data.
method Data-driven emergence of convolutional structure in neural networks.
result Initially fully-connected networks can learn convolutional structures from their inputs.
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. However, many defining characteris…
Proposes a fair meta-learning framework for few-shot classification.
problem Fairness in few-shot learning.
method Primal-Dual subgradient approach for fair initialization.
result Significant improvements over prior work in fairness.
Study invariant measures on measured laminations for subgroups of mapping class group.
problem Classify invariant Radon measures on space of measured laminations for subgroups of mapping class group.
method Geometric approach, focusing on recurrent measured laminations, explicitly constructing ergodic measures.
result Show uniquely ergodic for divergence-type subgroups, generalize results for full mapping class group.
New set-valued star-shaped risk measures introduced for better risk assessment.
problem Improving risk assessment in financial contexts.
method Developed new set-valued star-shaped risk measures and proved their representation theorems.
result Set-valued star-shaped risk measures can be represented as unions of set-valued convex risk measures.