On Reparameterizing the Score Function
Policy gradients for autoregressive sequence models differentiate each token's log-probability while holding the conditioning history fixed. This discards information about how earlier decisions…
deep-learning
MLINFO COLLECTION
品質予測
工程条件、原料ロット、検査値から品質指標や不良リスクを予測するための技術です。
記事一覧
18 / 27Unit-level aggregation breaks coverage in causal foundation models
Causal foundation models (CFMs) show promising results for treatment-effect estimation, with unit-level estimates that are competitive on standard benchmarks. Many causal analyses, however, inform…
nlp
HIFI: A Highly Efficient Framework for Statistical Inference with Foundation Models
Foundation models provide powerful representations for unstructured data, such as text and images, and parameter-efficient fine-tuning (PEFT) makes their adaptation to downstream tasks increasingly…
deep-learning
Prior-Data Fitted Networks for In-Context Off-Policy Evaluation
Off-policy evaluation (OPE) is essential for assessing decision policies before deployment when online experimentation is costly or unsafe. Accurate estimation remains difficult when behavior-policy…
nlp
The Information Geometry of Representation Formation
Most analyses of neural representations focus on trained endpoints, leaving the process by which internal structure forms comparatively unmeasured. We instead treat representation formation itself as…
deep-learning
From Common Information to Canonical Correlation Analysis and Beyond: Bridging Information Theory, Signal Processing, and Machine Learning
Many problems in signal processing, machine learning, and neuroimaging provide several jointly observed measurements of one process, each mixing a component common to all of them with a component…
machine-learning
Reinforced Iterative Learning Control for elastic joint arms: Guaranteed cross-trajectory generalization under model uncertainties
Trajectory tracking for compliant robots is challenging due to nonlinear dynamics and modeling uncertainties, often requiring learning-based methods to avoid explicit parameter identification.…
computer-vision
Stabilizing Filters for Graph Signal Generation
Generating graph signals is an important task in machine learning, and incorporating the underlying graph into a generative model enables structurally-informed distribution modeling. However, said…
deep-learning
Geometry-Aware Block Selection for Sparse Variational Gaussian Processes
Sparse variational Gaussian processes (SVGPs) are a widely used, principled approach to scalable Gaussian process modelling. Their success stems from their theoretically interpretable structure: they…
math-theory
What Moved the Alarm Score? Causal Attribution with Exact Computation and Scarce-Incident Estimation
Alarms in industrial systems and scientific instruments often demand immediate diagnosis despite scarce incident data. To guide intervention, an explanation must trace how changes in the…
computer-vision
IWOO: Wave Optics Optimizer Improved with Hybrid Strategies for Numerical Optimization and Engineering Applications
The Wave Optics Optimizer (WOO) incorporates optical diffraction and interference into numerical optimization and has shown competitive performance in benchmarks and engineering applications.…
nlp
Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents
Risk-sensitive reinforcement learning (RL) addresses decision-making under uncertainty and adverse outcomes. Learning risk-sensitive policies from fixed datasets is important when additional…
deep-learning
On the Error Analysis of Triangular Transport Maps for Conditional Generation via MMD-based Objectives
Conditional generative models parameterized by triangular transport maps are widely used for conditional sampling, yet theoretical guarantees on the quality of the conditional measures they produce…
nlp
Freezing Mechanism and Topology Dependence of Information Flow Structure in Small-Scale Particle Swarm Optimization
The neighborhood topology of particle swarm optimization (PSO) determines information propagation and regulates the exploration-exploitation balance. However, existing evaluation methods based on…
nlp
VampPrior Unleashed
Deep latent variable models (DLVMs) underpin many modern analysis pipelines, for example in single-cell genomics, yet their prior distributions have received markedly little attention. The VampPrior…
computer-vision
High-dimensional covariate-assisted ranking
Ranking data in modern applications often involves covariate vectors whose dimension grows with the number of objects. Identifying relevant covariates and integrating them with item-specific…
deep-learning
Bayesian Analysis of Inclusion Transaction Fee Mechanisms with Multiple Concurrent Proposers
The goal of this paper is to distill insight around the trade-offs present on Bayesian equilibria of transaction fee mechanism (TFM) design under $n$ multiple concurrent proposers (MCP). We…
deep-learning
R2-GP: Variance-Calibrated Priors for Additive Gaussian Processes
We develop R2-GP, an R2D2-type prior for Gaussian process (GP) generalised additive models (GAMs) that calibrates explained variance ($R^2$) for Matérn covariance kernels. The function variance for…
deep-learning
A Simple and General Approach to top-$k$ Selection
This paper considers the Bayesian top-$k$ identification problem, wherein a decision maker is tasked with selecting $k$ items from a pool of items of unknown quality. To assess the items, the…
computer-vision
Sustainable and Envy-free Multi-Period Allocation
Allocating renewable resources fairly requires accounting for how present decisions affect future availability. We introduce Sustainable and Envy-Free Multi-Period Allocation, in which agents are…
reinforcement-learning
Statistical Learning Theory for Direct Preference Optimization
Direct Preference Optimization (DPO) learns from pairwise preferences through a logistic objective whose score-difference parameterization follows the Bradley--Terry model. We study how failure of…
computer-vision
Fair Regression under Approximate Demographic Parity
Exact demographic parity requires the same prediction distribution across sensitive groups. In regression, this can be too restrictive and reduce predictive accuracy.
computer-vision
Peer-Relative Trust-Guided Update Screening for Robust Semi-Decentralized Federated Learning under Label-Flipping Attacks
Trust and reputation mechanisms can reduce the influence of malicious clients in federated learning (FL), but strict update filtering is difficult under non-independent and identically distributed…
deep-learning
Robust Direct Preference Optimization under Preference Label-Flip Attacks
Direct Preference Optimization (DPO) is widely used for offline Reinforcement Learning from Human Feedback. However, recent works have shown that DPO can be easily manipulated by adversarial…
reinforcement-learning