New algorithm tackles constrained Markov decision processes with peak constraints.
problem Optimizing dynamic systems with peak constraints.
method Model-free algorithm converting PCMDP to unconstrained problem, applying Q-learning.
result Algorithm achieves (ε,p)-PAC policy under certain conditions. We find empirically a characteristic sharp peak-flat trough pattern in a large set of commodity prices. We argue that the sharp peak structure reflects an endogenous inter-market organization, and that peaks may be seen as local ``singularities'' resulting from imitation and herding. These findings impose a novel strin…
A robust method for decomposing spectral peaks robust to distortion and interference.
problem Decomposing spectral peaks in the presence of distortion and interference.
method Optimizing a nonparametric approach using pseudo-symmetric functions with nonincreasing behavior.
result Decomposed spectral peaks show pseudo-orthogonal behavior and power preserving equality.
DePAint solves MARL for agents with local constraints, privacy, and no central controller.
problem Training multi-agent systems to optimize rewards while adhering to safety constraints in a decentralized setting.
method Formulated as a decentralized constrained multi-agent Markov Decision Problem, proposed DePAint method using momentum-based decentralized policy gradient.
result First privacy-preserving fully decentralized MARL algorithm considering both peak and average constraints.
New method separates model and non-model risks for more practical asset pricing.
problem Asset pricing under model-uncertainty.
method Binary model-risks and constraints over preferences; unique model-risk pricing formula.
result Unique model-risk pricing formula with dynamically conserved constant.
Paper proposes a network framework for prosumers to manage peak loads in Iran.
problem Balancing renewable prosumers' self-sufficiency with grid integration under uncertainty.
method Distributed contextual stochastic optimization (DCSO) framework with consensus-based sharing.
result Integration of prediction and optimization reduces peak loads and costs.
Weak lensing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables or via nonlinear transformations of the lensing field. Here we train and apply a 2D convolutional neural network to simulated noiseless lensi…
SPADE improves demand forecasting accuracy by 4.5% for post-promotion periods.
problem Overreacting to peak events in demand forecasting leads to biased forecasts.
method SPADE splits forecasting into two tasks: one for peak events and another for post-peak events, using masked convolution filters and a specialized Peak Attention module.
result Overall PPE improvement of 4.5%, 30% improvement for most affected forecasts after promotions and holidays, and 3.9% improvement in PE accuracy.
This paper develops the Jungle model in a credit portfolio framework. The Jungle model is able to model credit contagion, produce doubly-peaked probability distributions for the total default loss and endogenously generate quasi phase transitions, potentially leading to systemic credit events which happen unexpectedly …
Changepoint detection is a central problem in time series and genomic data. For some applications, it is natural to impose constraints on the directions of changes. One example is ChIP-seq data, for which adding an up-down constraint improves peak detection accuracy, but makes the optimization problem more complicated.…
Joint peak detection is a central problem when comparing samples in genomic data analysis, but current algorithms for this task are unsupervised and limited to at most 2 sample types. We propose PeakSegJoint, a new constrained maximum likelihood segmentation model for any number of sample types. To select the number of…
Mass spectrometry (MS) is an important technique for chemical profiling which calculates for a sample a high dimensional histogram-like spectrum. A crucial step of MS data processing is the peak picking which selects peaks containing information about molecules with high concentrations which are of interest in an MS in…
Study on-chain peak shaving to reduce Ethereum transaction costs.
problem Reducing transaction costs in blockchain networks, especially during congested periods.
method Analyzing transaction-level data from multiple firms across various industries to understand scheduling responses and cost management strategies.
result Firms' scheduling responses to congestion vary, leading to different fee savings and residual costs.
The paper explains two distinct peaks in generalization error for neural networks and simpler models, each governed by different factors.
problem Understanding the peaks in generalization error for neural networks and simpler models.
method Analysis of random feature models and comparison with numerical experiments involving deep neural networks.
result The peaks at N=P and N=D are distinct and governed by different factors (noise sensitivity vs. initialization noise). The heuristic identification of peaks from noisy complex spectra often leads to misunderstanding of the physical and chemical properties of matter. In this paper, we propose a framework based on Bayesian inference, which enables us to separate multipeak spectra into single peaks statistically and consists of two steps.…
We document and analyze the empirical facts concerning one of the clearest evidence of speculation in financial trading as observed in the postage collection stamp market. We unravel some of the mechanisms of speculative behavior which emphasize the role of fancy and collective behavior. In our conclusion, we propose a…
Study optimal consumption with drawdown limits over a fixed time frame.
problem Maximizing utility with consumption limits during a fixed period.
method Extended utility maximization problem with drawdown constraint, using PDE arguments and dual transform.
result Existence and uniqueness of classical solution to HJB variational inequality, with explicit free boundaries.
Bayesian framework integrates spectral deconvolution with expert reasoning for robust peak estimation.
problem Challenges in extracting meaningful peaks from noisy or complex spectra.
method Bayesian spectral deconvolution coupled with a physical-property regression layer.
result Recovery of weak peaks in poly(lactic acid) IR spectra related to degradation rates.
FLOPART solves peak detection by creating accurate train and test set predictions.
problem Correctly detecting peaks in sequential data.
method Dynamic programming changepoint algorithm with zero train label errors.
result FLOPART provides highly accurate predictions on both train and test sets.
The paper shows how the generalization curve can have multiple peaks, influenced by data and learning algorithm biases.
problem Understanding the generalization behavior of linear regression models under varying parameterizations.
method Analyzes generalization loss in linear regression models with varying parameterizations, both under- and over-parameterized.
result The generalization curve can have an arbitrary number of peaks, and their locations can be controlled.
PEAKS selects key training examples incrementally based on prediction error and kernel similarity.
problem Dynamic data selection in deep learning models.
method Prediction Error Anchored by Kernel Similarity (PEAKS) for incremental data selection.
result PEAKS outperforms existing selection strategies and yields better performance returns as training data size grows.
PEAK tests means of multiple data streams with sequential betting.
problem Testing means of multiple data streams with nonparametric methods.
method Sequential, nonparametric testing using a betting scheme.
result PEAK provides up to 85% reduction in samples for stopping.
Data analysis in high-dimensional spaces aims at obtaining a synthetic description of a data set, revealing its main structure and its salient features. We here introduce an approach providing this description in the form of a topography of the data, namely a human-readable chart of the probability density from which t…
LLMs learn peaked distributions slowly due to power-law losses.
problem Slow convergence of loss in training large language models.
method Systematic analysis of toy models and empirical evaluation of LLMs.
result Power-law time scaling with an exponent of 1/3 for learning peaked distributions.
Finite-time queue peaks in stochastic networks have logarithmic scaling after geometric thresholds.
problem Queue peak laws in stochastic networks with geometric thresholds.
method Self-normalization mechanism
result Logarithmic scaling of queue peaks after geometric thresholds.
Bayesian Quadrature improves ensembling for neural networks with dispersed likelihood peaks.
problem Ensembling neural networks struggles with dispersed, narrow peaks in likelihood surfaces.
method Uses Bayesian Quadrature to construct weighted ensembles of architectures.
result Empirically outperforms state-of-the-art baselines in test likelihood, accuracy, and expected calibration error.
During a stock market peak the price of a given stock (i) jumps from an initial level p1(i) to a peak level p2(i) before falling back to a bottom level p3(i). The ratios A(i)=p2(i)/p1(i) and B(i)=p3(i)/p1(i) are referred to as the peak- and bottom-amplitude respectively. The paper show…
In this paper, the fractional order curvature equation (−Δ)γu=(1+εK(x))uN−2γN+2γ in RN is considered. Assuming K(x) has two critical points satisfying certain local conditions, we prove the existence of two-peak solutions.
A nonparametric method for time series analysis extracts envelopes, detects peaks, and clusters data.
problem Extracting envelopes, detecting peaks, and clustering in time series data.
method Iterative procedure that minimizes L1 drift to create upper and lower bounding signals, using Viterbi-like path tracking and optimal elimination rules. result Efficiently calculated solution with near-linear time complexities for various applications.
Populations of species in ecosystems are often constrained by availability of resources within their environment. In effect this means that a growth of one population, needs to be balanced by comparable reduction in populations of others. In neutral models of biodiversity all populations are assumed to change increment…
Traditionally in regression one minimizes the number of fitting parameters or uses smoothing/regularization to trade training (TE) and generalization error (GE). Driving TE to zero by increasing fitting degrees of freedom (dof) is expected to increase GE. However modern big-data approaches, including deep nets, seem to…
We win EVA2025 by estimating extreme precipitation events using Peaks Over Thresholds and martingale testing.
problem Estimating the probability of extreme precipitation events with limited data.
method Modeling Peaks Over Thresholds with an exponential distribution and using martingale testing for evaluation.
result Our method outperforms other approaches in estimating extreme precipitation events.
Recomputation algorithms collectively refer to a family of methods that aims to reduce the memory consumption of the backpropagation by selectively discarding the intermediate results of the forward propagation and recomputing the discarded results as needed. In this paper, we will propose a novel and efficient recompu…
This paper explains why double descent sometimes occurs weakly or not at all from an optimization perspective.
problem Understanding the role of optimization in the phenomenon of double descent.
method Investigates model-wise double descent from an optimization perspective, proposing a unified explanation for its occurrence.
result Model-wise double descent is observed if and only if the optimizer can find a sufficiently low-loss minimum.
Support Vector Data Description (SVDD) provides a useful approach to construct a description of multivariate data for single-class classification and outlier detection with various practical applications. Gaussian kernel used in SVDD formulation allows flexible data description defined by observations designated as sup…
Modeling consumption and investment decisions with reference point and drawdown constraints.
problem Modeling consumption and investment decisions with reference point and drawdown constraints.
method Solving a stochastic control problem to derive value function, optimal consumption plan, and investment strategy in semi-explicit forms.
result Five important thresholds of wealth, all as functions of h, and significant economic implications. Two new methods improve monotonic constraint enforcement in regression and classification trees.
problem Improving monotonic constraints in regression and classification trees.
method Proposed two new methods: one yields better results than LightGBM, the other yields even better results but is slower.
result The best method consistently beats the current implementation of LightGBM, achieving up to 1% loss reduction.
A new clustering algorithm reduces density peaks clustering's computational complexity.
problem High computational complexity of density peaks clustering.
method Sparse distance matrix, sparse search, K-d tree, second-order difference method.
result Reduced computational complexity from O(n2K) to O(n(n1−1/K+k)). Paper proposes combining GAM and DNN for accurate peak demand estimation from lower-resolution data.
problem Predicting high-resolution peak demand from limited lower-resolution data.
method Combines generalized additive models (GAM) and deep neural networks (DNN) for half-hourly load forecasting.
result Proposed method reduces out-of-sample RMSE by 57.4% compared to benchmark.
We study the dynamics of order flows around large intraday price changes using ultra-high-frequency data from the Shenzhen Stock Exchange. We find a significant reversal of price for both intraday price decreases and increases with a permanent price impact. The volatility, the volume of different types of orders, the b…
Serenity optimizes neural network execution for edge devices by scheduling with optimal memory footprint.
problem Order of nodes in irregular neural networks affects memory footprint, complicating execution under resource constraints.
method Memory-aware compiler using dynamic programming and graph rewriting to find optimal schedules.
result Achieves optimal peak memory and further improves it with graph rewriting, reducing memory usage by 1.68x-1.86x compared to TensorFlow Lite.
Improved peak detection in ChIP-seq data reduces over-dispersion.
problem Over-dispersion in ChIP-seq data reduces peak detection accuracy.
method Supervised segmentation models with alternative noise assumptions.
result Improved peak detection accuracy compared to natural assumptions.
New model improves volatility forecasting by reducing overestimation and underestimation.
problem SVR-GARCH model overestimates or underestimates volatility, hindering peak or trough behaviors.
method Proposes blending ARCH and augmented blending-ARCH models to improve volatility forecasting.
result Empirical results show improved volatility forecasting ability.
Extracts important peaks from XRD spectra using Attention mechanism.
problem Identifying significant peaks in XRD patterns for material properties.
method Convolutional neural network with Attention mechanism to analyze deep features.
result Selected lattice constant predicts cathodic material cell voltage.
During a speculative episode the price of an item jumps from an initial level p_1 to a peak level p_2 before more or less returning to level p_1. The ratio p_2/p_1 is referred to as the amplitude A of the peak. This paper shows that for a given market the peak amplitude is a linear function of the logarithm of the pric…
Deep Learning is applied to energy markets to predict extreme loads observed in energy grids. Forecasting energy loads and prices is challenging due to sharp peaks and troughs that arise due to supply and demand fluctuations from intraday system constraints. We propose deep spatio-temporal models and extreme value theo…
Study on convergence rate of Bergman metrics on Kähler manifolds.
problem Analyzing convergence rate of Bergman metrics on Kähler manifolds.
method Using Tian's peak section method to show uniform C1,α convergence. result Uniform C1,α convergence of Bergman metrics is demonstrated. Efficient neural Bayes estimators for censored peaks-over-threshold models improve inference speed and accuracy.
problem Computational burden in inference with spatial extremal dependence models due to intractable or censored likelihoods.
method Developed neural Bayes estimators using data augmentation techniques to encode censoring information.
result Significant gains in computational and statistical efficiency compared to traditional methods.