A new method for efficient label retrieval in large output spaces.
problem Efficiently retrieving relevant labels for inputs with large output spaces.
method Developed a technique called Stochastic Negative Mining to address the problem of set-valued classifiers in large output spaces.
result Stochastic Negative Mining outperforms existing negative sampling approaches in experiments.
Paper connects sampling and labeling biases in large-output spaces.
problem Efficient training in large-output spaces with label imbalance.
method Unified approach to address sampling and labeling biases.
result Different negative sampling schemes trade-off performance on dominant and rare labels.
A new method quantizes output space for multi-target regression.
problem Predicting multiple continuous targets using shared predictors.
method MRQ method that quantizes output space to model dependencies and scale.
result MRQ achieves high scalability and competitive accuracy.
Sig-PCA integrates model outputs and observations to correct model biases.
problem Improving model accuracy and reliability by correcting biases and numerical approximations.
method Sig-PCA framework that combines summary statistics from model outputs with localized observations via a neural network.
result Corrects model outputs to align closely with observational data, preserving essential statistical information.
The paper presents a novel approach to multi-output regression using probabilistic circuits.
problem Capturing correlations between multiple output dimensions in large-scale regression problems.
method Employing a mixture of single-output Gaussian process experts encoded via a probabilistic circuit.
result The method can capture correlations between output dimensions and often outperforms other approaches.
New method learns output embeddings for structured prediction.
problem Structured prediction with output embeddings.
method Jointly learns output embedding and regression function.
result Structured predictor is a consistent estimator with smaller complexity.
Paper improves generalization bounds for structured output prediction problems.
problem Large label sets in structured output prediction problems.
method Developed novel high-probability bounds and generalization bounds in expectation.
result Significantly improved generalization bounds with logarithmic dependency on label set size.
A scalable method for Bayesian inference in large linear models.
problem High computational cost in Bayesian linear models for large networks.
method Sample-based inference and g-prior for hyperparameter selection.
result Linearised neural network inference on large datasets (ResNet-18, ResNet-50, U-Net).
Study efficient interactive learning for structured outputs with reliable computation.
problem Interactive learning with noisy labels and structured output spaces.
method Identify and utilize CRISPs (probabilistic models) that guarantee reliable and efficient computation of probabilistic quantities.
result CRISPs enable robust and efficient active and skeptical learning in large structured output spaces.
A new framework for structured prediction on non-vectorial spaces.
problem Structured prediction on non-vectorial output spaces.
method Defining a suitable geometry for implicit loss functions.
result Efficient algorithmic framework with sharp statistical analysis.
Combines neural networks with variational inference for better uncertainty quantification.
problem Overconfident predictions from traditional neural networks and time-consuming Bayesian optimization.
method VIFO (Variational Inference on the Final-Layer Output) using neural networks to learn mean and variance.
result VIFO provides a good tradeoff in run time and uncertainty quantification, especially for out of distribution data.
New model handles complex output dependence in large datasets.
problem Complex output dependence in large datasets.
method Orthogonal Stochastic Linear Mixing Model (OSLMM) with Markov chain Monte Carlo inference.
result OSLMM reduces prediction error compared to state-of-the-art methods.
Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces. In this paper, we focus on reducing the prediction time of a trained black-box structured classifier without losing accuracy. To do so, we train a speedup classifier that learns to mimic a black-box classifier u…
DBPA assesses LLM perturbations using frequentist hypothesis testing.
problem Quantifying input perturbation impacts on LLM outputs.
method DBPA reformulates perturbation analysis as frequentist hypothesis testing, using Monte Carlo sampling for empirical null and alternative distributions.
result DBPA provides interpretable p-values and scalar effect sizes for LLM perturbations.
TCNs can approximate complex input-output maps with limited memory.
problem Approximating complex input-output maps with limited memory.
method Proved TCNs can approximate a wide class of input-output maps with arbitrary error tolerance.
result Deep ReLU TCNs can approximate input-output maps with finite memory to arbitrary error.
Prototype networks on hyperspheres improve classification and regression.
problem Improving classification and regression performance.
method Using hyperspherical prototypes for classification and regression, optimizing prototypes through data-independent margin separation.
result Hyperspherical prototype networks outperform other methods in classification, regression, and their combination.
Within machine learning, the supervised learning field aims at modeling the input-output relationship of a system, from past observations of its behavior. Decision trees characterize the input-output relationship through a series of nested if−then−else questions, the testing nodes, leading to a set of predictions, th…
Efficiently approximates uncertainty in classification models using Dirichlet distributions.
problem Inefficient computation of uncertainty estimates in Bayesian deep learning.
method Revised Laplace Bridge method to construct a Dirichlet approximation of softmax output distributions.
result The Dirichlet approximation leads to more efficient computation and better uncertainty estimates.
Extreme classification problems are multiclass and multilabel classification problems where the number of outputs is so large that straightforward strategies are neither statistically nor computationally viable. One strategy for dealing with the computational burden is via a tree decomposition of the output space. Whil…
Adaptive tuning of latent space for non-stationary data.
problem Learning from large, non-stationary systems with quick characteristic changes.
method Adaptive tuning of low-dimensional latent space based on real-time feedback.
result Improved prediction of time-varying charged particle beam properties.
Unified approach to structured prediction combining entropy regularization and neuro-symbolic logic.
problem Structured prediction challenges due to large output spaces and insufficient labeled data.
method Neuro-symbolic entropy regularization loss that restricts entropy regularization to valid structures.
result Models predict more accurately and are more likely to be valid.
Gaussian processes (GPs), or distributions over arbitrary functions in a continuous domain, can be generalized to the multi-output case: a linear model of coregionalization (LMC) is one approach. LMCs estimate and exploit correlations across the multiple outputs. While model estimation can be performed efficiently for …
LLMs produce volatile sentence-level sentiment classifications that affect financial decision-making.
problem Volatile outputs from LLMs impact financial text understanding tasks.
method Case study on US equity market investing via news sentiment analysis.
result Volatile LLM outputs lead to significant variations in portfolio construction and returns.
Inference in log-linear models scales linearly in the size of output space in the worst-case. This is often a bottleneck in natural language processing and computer vision tasks when the output space is feasibly enumerable but very large. We propose a method to perform inference in log-linear models with sublinear amor…
Conditional generative adversarial networks (cGAN) have led to large improvements in the task of conditional image generation, which lies at the heart of computer vision. The major focus so far has been on performance improvement, while there has been little effort in making cGAN more robust to noise. The regression (o…
New method speeds up Bayesian inference for complex simulators.
problem Challenges in Bayesian inference for complex stochastic simulators with intractable likelihood functions.
method Optimization Monte Carlo framework reformulated as deterministic optimization problems with gradient-based methods.
result Accurate posterior inference with reduced runtimes compared to existing methods.
Many structured prediction problems (particularly in vision and language domains) are ambiguous, with multiple outputs being correct for an input - e.g. there are many ways of describing an image, multiple ways of translating a sentence; however, exhaustively annotating the applicability of all possible outputs is intr…
Sketching accelerates structured prediction methods for large datasets.
problem Scaling surrogate kernel methods for large datasets.
method Sketching approximations applied to input and output feature maps.
result Achieves close-to-optimal rates with reduced sketch size.
A new loss function speeds up sequence-to-sequence models for continuous outputs.
problem Slow and memory-intensive softmax layer limits vocabulary size and translation quality.
method Proposes a probabilistic loss and continuous embedding layer training/inference procedure.
result Models achieve up to 2.5x speed-up in training time with similar translation quality.
Structured prediction tasks pose a fundamental trade-off between the need for model complexity to increase predictive power and the limited computational resources for inference in the exponentially-sized output spaces such models require. We formulate and develop the Structured Prediction Cascade architecture: a seque…
Efficiently samples sequences without replacement for machine learning models.
problem Generating diverse outputs from sequential models without duplicates.
method Incremental sampling procedure for randomized programs, including neural models.
result Efficacy and flexibility of incremental sampling for large output spaces.
A scalable method for efficient inference in Gaussian process regression networks.
problem Intractable inference in Gaussian process regression networks (GPRN).
method Tensorization of output space, tensor/matrix-normal variational posteriors, joint optimization, and exploiting Kronecker product structure.
result Captures posterior dependencies and improves inference quality for large number of outputs.
Aims to optimize complex multivariate systems with constraints.
problem Optimizing force-field systems in physics with large-scale simulations.
method Combines machine learning and experimental design to find feasible input combinations.
result Locates multiple good regions in the input space.
The study addresses negative transfer in multi-output Gaussian processes by proposing latent structures.
problem Negative transfer in multi-output Gaussian processes leading to decreased performance.
method Defining negative transfer, deriving conditions for avoiding it, proposing latent structures.
result Latent structures can avoid negative transfer and scale to large datasets.
A scalable MOGP model with stochastic variational inference for many outputs.
problem Efficiently modeling data from multiple sources with many outputs.
method Stochastic variational inference for Latent Variable MOGP (LV-MOGP).
result Computational complexity per iteration is independent of the number of outputs.
OC-BNNs enforce output constraints in BNNs, improving model robustness.
problem Hard to encode prior knowledge in function space for BNNs.
method Formulate a prior that incorporates functional constraints on output.
result OC-BNNs improve model robustness and prevent infeasible predictions.
The study shows removing fully connected output layers improves efficiency without sacrificing performance.
problem Large number of parameters in fully connected layers for high-category datasets.
method Examined architectures replacing fully connected output layers with fixed layers and compared performance.
result Fixed classifiers offer no additional benefit over removing the output layer and its parameters.
Proposes a method for evaluating multiple dimensions of organizational effectiveness using DEA.
problem Evaluating multiple dimensions of organizational effectiveness in large data sets.
method Introduces two regularized DEA models (SBM and GP-SBM) to estimate both dimension-specific and aggregate efficiency scores.
result Demonstrates improved efficiency and validity compared to conventional methods.
Study shows limitations and possibilities of learning quantum circuit output distributions.
problem Learnability of output distributions of local quantum circuits.
method Investigated within two oracle models: statistical query model and direct sample access model.
result Output distributions of super-logarithmic depth Clifford circuits are not efficiently learnable in the statistical query model.
The paper proves neural networks with ReLU and softmax can approximate any function.
problem Approximating functions and class labels in neural networks.
method Extended universal approximator theory to neural networks with ReLU and softmax.
result Neural networks with ReLU and softmax can approximate any function and class labels.
Regression problems are pervasive in real-world applications. Generally a substantial amount of labeled samples are needed to build a regression model with good generalization ability. However, many times it is relatively easy to collect a large number of unlabeled samples, but time-consuming or expensive to label them…
Gradient flow in parameters equals linear interpolation in outputs.
problem Understanding and optimizing training algorithms in deep learning.
method Proving equivalence between gradient flow in parameter space and linear interpolation in output space, and deriving formulas for global minima.
result Gradient flow in parameters can be transformed into linear interpolation in outputs, leading to global minima.
Study reveals pathological eigenvalue spectra in FIM and its variants of DNNs.
problem Understanding sharp local shapes in DNN loss landscapes.
method Analysis of FIM and its variants in regression and classification DNNs.
result Pathological eigenvalue spectra appear in FIM and its variants, indicating sharp local shapes in specific directions.
Hierarchical Softmax approximates class probabilities for large datasets efficiently.
problem Computational inefficiency of Softmax for large-scale classification tasks.
method Used Hierarchical Softmax to approximate class probabilities efficiently.
result Hierarchical Softmax performance degrades as the number of classes increases.
Improves active learning efficiency by warping input space based on observed outputs.
problem Insensitivity of Gaussian process uncertainty to actual observations.
method Input warping with learned monotone reparameterization to adjust acquisition function behavior.
result Significantly improved sample efficiency across various benchmarks, especially in non-stationary conditions.
Transflow Learning transforms pre-trained models without retraining.
problem Transforming pre-trained models without retraining.
method Bayesian inference to warp latent vector probability distribution.
result Transforms model outputs to resemble new data without training.
E2M predicts metric space outputs using deep learning.
problem Predicting non-Euclidean outputs like distributions and matrices.
method Weighted Fréchet means over learned weights.
result E2M achieves state-of-the-art performance across various outputs.
The standard margin-based structured prediction commonly uses a maximum loss over all possible structured outputs. The large-margin formulation including latent variables not only results in a non-convex formulation but also increases the search space by a factor of the size of the latent space. Recent work has propose…