No-Regret Language Generation
We introduce no-regret generation, which requires a generator to make a sublinear number of mistakes uniformly over all demonstration sequences and compatible target languages. We also formulate an…
machine-learning
MLINFO COLLECTION
Sensor Data Analysis
センサ、時系列、異常検知、予測保全に使える機械学習・深層学習技術をまとめます。
記事一覧
8 / 8On the Convergence of Iterated Round Robin
Round Robin (RR) is a simple and widely used picking sequence mechanism for allocating indivisible goods, known to guarantee envy-freeness up to one item (EF1) when preferences are additive. Despite…
machine-learning
Evolve on the Host, Predict on the Edge: Deploying Online Neuroevolutionary Architecture Search for Cross-sectional Stock Return Prediction
Accurate forecasting models are usually large, expensive to update online, and fixed in architecture once trained. We apply ONE-NAS, an online neuroevolutionary architecture search that evolves a…
deep-learning
Explicit Asymptotic Bounds for Sequential Calibration Beyond $T^{2/3}$
Probability forecasts are calibrated when predicted probabilities match empirical outcome frequencies: among events assigned a probability $p$, we'd hope that the fraction of positive outcomes is…
generative-ai
The Investment Acceleration Principle Revisited by means of a Neural Network
The investment acceleration principle is a heuristic for modelling investment time series out of consumption time series. The model presented herein develops a disaggregated accelerator equation…
deep-learning
Graph neural networks for sampling-invariant embeddings of organized signal sets
Sensor networks and radars can deliver signals as organized sets, e.g. ordered signals, signals describing range cells within a grid or signals perceived as graph nodes.
deep-learning
MAPLE: Mondrian-Anchored Prior for Learning-free Indoor Exploration
Robots exploring unknown indoor environments must decide where to move while much of the environment remains unseen. Predicting the occupancy of unseen space beyond the current sensor range can…
deep-learning
MARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and Autonomy
Lunar surface exploration increasingly relies on autonomous rovers that must perceive and traverse unstructured terrain under extreme illumination conditions. Near the lunar poles, low sun elevations…
nlp
Active Pilot Sampling for Multi-fidelity Estimation in Stochastic Optimization
Stochastic optimization with high-fidelity nonlinear models is often computationally prohibitive because each objective evaluation requires sampling-based uncertainty quantification inside an outer…
computer-vision
Robust Covariance Estimation for Entry-wise Contaminated and Partially Observed Data via Expectation Maximization Algorithm
Robust covariance estimation under entry-wise contamination and missing data is challenging in various signal processing applications. Under the Student-$t$ model, observation-level reweighting…
computer-vision
WhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecasting
Recent time series foundation models (TSFMs) can consume covariates in-context, extending zero-shot forecasting to problems driven by external factors. This enables scenario analysis: forecasting how…
nlp
Online Fair Division with Upgrade Recourse
We study the online fair division of indivisible goods. In the standard model, where assignments are irrevocable, no algorithm can guarantee any positive fraction of the maximin share (MMS).
machine-learning
Morpheus-2.0: Multiscale Probabilistic Forecasting with Dual-Axis Attention
A universal forecaster is trained once and applied everywhere, so it must serve tasks whose schemas, forecast horizons, and temporal resolutions all differ. The number of targets and covariates…
computer-vision
Margin Certificates for Voting Classifiers under Mixing Dependence
Margin bounds explain why weighted votes generalize after training error vanishes, but dependent observations require concentration arguments that keep the dependence model and failure budget…
nlp
The Loss or the Architecture? What Matters in Survival Analysis with Competing Risks
Often, \emph{eg} in healthcare and predictive maintenance, what matters is which of several competing causes will strike first, and with what probability: survival analysis with competing risks.…
machine-learning
Matched Specialization, Different Adaptation: Second-Moment Structure in Shared Representations
Small Adam-trained shared-representation networks can reach equivalent selected mean readout measurements yet respond differently to the same further learning. We use state interventions to separate…
deep-learning
Is a Linear Probe Evidence of a Linear Representation?
The linear representation hypothesis holds that pretrained vision models encode generative factors as linearly decodable directions in feature space, and comes with a standard methodology: train a…
deep-learning
Forecast Accuracy Is Not Trading Profit: Evolving Small Recurrent Networks for Stock Return Prediction
Time series forecasting models are typically compared on pointwise error, which scores a prediction in isolation from the decision it is produced for, and a lower forecast error does not imply a…
deep-learning
Self-Repairing Recurrent Ensembles for Real-Time Recovery from Distribution Shift
Deploying a pretrained controller exposes it to conditions that are absent from its training data. Sensor drift, outright sensor failure and accumulating measurement noise all induce a distribution…
deep-learning
Neuron-Level Architecture Growth: A Controlled Evaluation for EEG Time-Series Decoding
Convolutional EEG decoders are trained at a fixed width, usually set by their authors on other data. Growing methods add neurons during training where the loss could decrease the most, but whether…
deep-learning