Full-batch GD outperforms one-pass SGD in learning a single-index model with quadratic activation.
problem Learning a single-index model with quadratic activation using gradient descent.
method Full-batch gradient descent compared to one-pass stochastic gradient descent (SGD) on a correlation loss.
result Full-batch GD requires only n≃d samples for strong recovery, while one-pass SGD requires n≳dlogd samples. Single-pass method estimates neural network uncertainty.
problem Uncertainty estimation in deep learning requires multiple passes.
method Probabilistic reasoning over neural network depths.
result Single forward pass for uncertainty estimation.
New algorithm accelerates single-pass SGD for generalized linear prediction.
problem Improving single-pass non-quadratic stochastic optimization.
method Data-dependent proximal method incorporating dual-momentum acceleration.
result Momentum acceleration resolves open problem in streaming setting.
We consider stochastic gradient descent (SGD) for least-squares regression with potentially several passes over the data. While several passes have been widely reported to perform practically better in terms of predictive performance on unseen data, the existing theoretical analysis of SGD suggests that a single pass i…
SPACR trains uncertainty-aware regressors directly within a single pass, improving efficiency and validity.
problem Training uncertainty-aware regressors while maintaining efficiency and validity.
method Joint optimization of efficiency and validity during training.
result SPACR consistently provides tighter intervals and better coverage-efficiency trade-offs compared to standard CP and DOICR.
Improved single-pass streaming MAB regret bound to O(K^1/3T^2/3).
problem Minimize regret in single-pass streaming multi-armed bandits with sublinear memory.
method Improved regret lower bound to Ω(K^1/3T^2/3) and upper bound to O(K^1/3T^2/3).
result Achieved tight regret bound of O(K^1/3T^2/3) for algorithms with o(K) memory.
A new single-pass algorithm improves sparse PCA under limited computational resources.
problem Sparse PCA with limited computational budget.
method Thresholding Oja's algorithm output.
result Achieves minimax error bound in O(d) space and O(nd) time.
Single deep model detects out-of-distribution data with single forward pass.
problem Detecting out-of-distribution data points in neural networks.
method Deterministic uncertainty quantification (DUQ) using gradient penalty for reliable detection.
result Single model outperforms or matches ensemble methods in out-of-distribution detection.
Simple neural net outperforms complex uncertainty methods.
problem Reliable uncertainty estimation from deterministic models.
method A simple baseline using a single softmax neural net with residual connections and spectral normalization.
result Simple neural net outperforms DUQ and SNGP on uncertainty prediction.
In this paper we present a new algorithm for computing a low rank approximation of the product ATB by taking only a single pass of the two matrices A and B. The straightforward way to do this is to (a) first sketch A and B individually, and then (b) find the top components using PCA on the sketch. Our algori…
Proposes a deep model for Bayesian quantile regression without Gaussian assumptions.
problem Uncertainty quantification from single forward-pass models is computationally expensive and restrictive.
method Deep evidential learning for Bayesian quantile regression.
result Achieves calibrated uncertainties on non-Gaussian distributions.
We present a streaming model for large-scale classification (in the context of ℓ2-SVM) by leveraging connections between learning and computational geometry. The streaming model imposes the constraint that only a single pass over the data is allowed. The ℓ2-SVM is known to have an equivalent formulation in …
A new classifier encodes local neighborhoods for each class using Fly Bloom Filters.
problem Efficiently classify data with single-pass learning.
method Proposes a new classifier that encodes local neighborhoods for each class with per-class Fly Bloom Filters.
result The proposed classifier's performance is competitive with nearest-neighbor classifiers and other single-pass classifiers.
A new model improves uncertainty estimation in deep learning.
problem Deep Kernel Learning (DKL) produces unreliable uncertainty estimates.
method Proposed a bi-Lipschitz constraint to preserve distances in feature space.
result DUE model outperforms previous DKL and other methods in uncertainty quality.
New framework models uncertainty in classification debates.
problem Weak interpretability of existing uncertainty quantification methods.
method Courtroom analogy and Mixture of Dirichlet Experts (MoDEX) model.
result MoDEX achieves state-of-the-art uncertainty quantification performance.
Proposes PSCs for UQ in deep nets without retraining.
problem Estimating uncertainty in deep nets with a single pass.
method Identifies sensitive, smooth intermediate layer, fits probabilistic model.
result PSCs achieve UQ and OOD detection performance matching existing methods.
New MCMC algorithm reduces subset selection passes to 2 for optimal k-dimensional subspace approximation.
problem Subset selection for k-dimensional subspace approximation with ε-approximation. method MCMC sampling algorithm reducing passes to 2 for p=2 case, poly(k/ε) size subset. result Subset selection of nearly optimal size in 2 passes, (1+ε) approximation. PFP-BNNs offer a fast, deterministic approach to Bayesian neural networks.
problem Limited uncertainty handling in traditional neural networks restricts their use in safety-critical settings.
method Probabilistic Forward Pass (PFP) approximates Stochastic Variational Inference (SVI) for efficient BNNs.
result PFP-BNNs achieve up to 4200x speedup over SVI-BNNs while maintaining similar accuracy and uncertainty.
Two-layer networks learn faster with batch reuse, overcoming information and leap exponents.
problem Limitations of gradient flow and single-pass GD in learning multi-index target functions.
method Multi-pass gradient descent that reuses batches, analyzed using Dynamical Mean-Field Theory.
result Two-time-step overlap with target subspace for non-staircase functions, overcoming information and leap exponents.
Single model predicts multiple subnetworks for robustness.
problem Efficiently ensemble neural networks for robustness and uncertainty.
method Multi-input multi-output (MIMO) configuration to train independent subnetworks.
result Significant improvement in negative log-likelihood, accuracy, and calibration error.
PySAD offers a unified Python framework for efficient streaming anomaly detection.
problem Efficient anomaly detection in streaming data with strict constraints.
method Unified architecture with 17+ streaming algorithms, specialized components, and support for multiple learning paradigms.
result PySAD enables real-time processing with bounded memory and is compatible with other Python frameworks.
This paper analyzes multi-pass SGD for least squares, improving generalization bounds.
problem Improving generalization bounds for multi-pass SGD in the least squares problem.
method Develops an instance-dependent excess risk bound for least squares in the interpolation regime.
result SGD performs worse than GD instance-wise but saves computational time.
FinReflectKG builds a comprehensive financial knowledge graph from SEC filings, improving extraction quality.
problem Lack of large-scale, open-source financial knowledge graph datasets.
method Intelligent document parsing, table-aware chunking, schema-guided iterative extraction, reflection-driven feedback loop.
result Reflection-agent-based mode achieves best balance of efficiency, accuracy, and reliability.
One-pass private sketch supports various machine learning tasks.
problem Efficiently supporting multiple machine learning tasks with differential privacy.
method Randomized contingency tables indexed with locality-sensitive hashing, constructed in one pass.
result Competitive error bounds for DP kernel density estimation, faster than existing methods.
We use the terms, knot product and local move, as defined in the text of the paper. Let n be an integer≧3. Let Sn be the set of simple spherical n-knots in Sn+2. Let m be an integer≧4. We prove that the map j:S2m→S2m+4 is bijective, where j(K)=K⊗Hop…
Unified theory linking atom-centered and message-passing models for molecular properties.
problem Combining atom-centered and message-passing models for accurate molecular property prediction.
method Generalizing ACDC framework to include multi-centered information, providing a complete linear basis for regression.
result Unified understanding of atom-centered and message-passing models, providing a coherent foundation.
XIMP improves molecular property prediction by integrating multiple graph representations.
problem Graph neural networks struggle in data-scarce regimes and fail to surpass traditional methods.
method Cross-graph inter-message passing with multiple graph abstractions.
result XIMP outperforms state-of-the-art baselines across diverse molecular property tasks.
New algorithm reduces memory usage for multi-pass bandit problems.
problem Memory-efficient multi-pass bandit algorithms for large action spaces.
method Develops a B-pass algorithm with O(1) memory that achieves optimal regret. result Sharp memory-regret trade-off: O(1) memory suffices for Θ(T1/2) regret in B passes. BankGCN improves graph convolution networks by handling multi-channel signals with adaptive filter banks.
problem Handling multi-channel graph signals with limited architectures.
method BankGCN decomposes multi-channel signals into subspaces and uses adapted filters for each subspace.
result BankGCN achieves excellent performance in graph classification on benchmark datasets.
We introduce graph normalizing flows: a new, reversible graph neural network model for prediction and generation. On supervised tasks, graph normalizing flows perform similarly to message passing neural networks, but at a significantly reduced memory footprint, allowing them to scale to larger graphs. In the unsupervis…
Unified policy controls diverse agents through modular neural networks.
problem Learning control policies for various agent morphologies.
method Shared Modular Policies (SMP) with decentralized control and message passing.
result A single modular policy controls multiple agent morphologies.
SGD converges with perturbed forward-backward passes, explained by geometric amplification.
problem Analyzing convergence of SGD with perturbed forward-backward passes in composite optimization.
method Characterized propagation and amplification of perturbations, derived convergence guarantees for non-convex and PL objectives.
result Perturbations cascade through the computational graph, affecting convergence order under specific conditions.
Paper introduces efficient uncertainty estimation in LLMs without multiple forward passes.
problem Accurate uncertainty quantification in LLMs remains challenging.
method Evidential Knowledge Distillation to create compact student models.
result Efficient uncertainty estimation achieved with single forward pass.
Generative networks implicitly approximate complex densities from their sampling with impressive accuracy. However, because of the enormous scale of modern datasets, this training process is often computationally expensive. We cast generative network training into the recent framework of compressive learning: we reduce…
PushNet efficiently and adaptively pushes messages in neural networks, improving performance.
problem Inefficient and inflexible synchronous message passing in neural networks.
method Asynchronous message passing with adaptive receptive fields and multiple scale correlations.
result PushNet outperforms competitors in semi-supervised node classification on multiple datasets.
Kernel Three-Pass Regression Filter improves forecasting efficiency for nonlinear dependencies.
problem Forecasting with high-dimensional predictors and latent factors.
method Developed a new estimator, Kernel Three-Pass Regression Filter (K3PRF), to address nonlinear dependencies.
result Empirically shows significant improvement in long-term forecasting performance.
In many estimation problems, e.g. linear and logistic regression, we wish to minimize an unknown objective given only unbiased samples of the objective function. Furthermore, we aim to achieve this using as few samples as possible. In the absence of computational constraints, the minimizer of a sample average of observ…
GAMformer bridges tabular models and interpretability, offering a single-pass approach.
problem Lack of interpretability in tabular foundation models like TabPFN.
method In-context learning for GAM shape functions, training on synthetic data.
result GAMformer performs comparably to other leading GAMs across various classification benchmarks.
UCPO improves diversity in reinforcement learning models, maintaining high accuracy.
problem RLVR objectives often lead to diversity collapse, reducing coverage of correct solutions.
method UCPO adds a conditional uniformity penalty to GRPO, redistributing probability mass.
result UCPO improves Pass@K and diversity while maintaining competitive Pass@1 accuracy.
Proposes integrating global and local entropy for more reliable LLMs.
problem Uncertainty in large language models (LLMs) leads to unreliable predictions.
method Measures global uncertainty from hidden-state matrices and local uncertainty from tokens, combining them via a multiplicative gate.
result Global-Local Uncertainty (GLU) outperforms unsupervised baselines across multiple models and benchmarks.
As deep neural networks are increasingly being deployed in practice, their efficiency has become an important issue. While there are compression techniques for reducing the network's size, energy consumption and computational requirement, they only demonstrate empirically that there is no loss of accuracy, but lack for…
FinReflectKG - EvalBench benchmarks financial KG extraction from SEC 10-K filings.
problem Lack of universal benchmark and evaluation framework for financial KG construction.
method Agentic and holistic evaluation principles, deterministic commit-then-justify judging protocol, binary and ordinal evaluations.
result Reflection-based extraction outperforms single-pass extraction in comprehensiveness, precision, and relevance.
We introduce an efficient message passing scheme for solving Constraint Satisfaction Problems (CSPs), which uses stochastic perturbation of Belief Propagation (BP) and Survey Propagation (SP) messages to bypass decimation and directly produce a single satisfying assignment. Our first CSP solver, called Perturbed Blief …
We propose a new variational inference algorithm for learning in Gaussian Process State-Space Models (GPSSMs). Our algorithm enables learning of unstable and partially observable systems, where previous algorithms fail. Our main algorithmic contribution is a novel approximate posterior that can be calculated efficientl…
Neural networks offer high-accuracy solutions to a range of problems, but are costly to run in production systems because of computational and memory requirements during a forward pass. Given a trained network, we propose a techique called Deep Learning Approximation to build a faster network in a tiny fraction of the …
Parameterised actions in reinforcement learning are composed of discrete actions with continuous action-parameters. This provides a framework for solving complex domains that require combining high-level actions with flexible control. The recent P-DQN algorithm extends deep Q-networks to learn over such action spaces. …
We introduce a new framework for unsupervised learning of representations based on a novel hierarchical decomposition of information. Intuitively, data is passed through a series of progressively fine-grained sieves. Each layer of the sieve recovers a single latent factor that is maximally informative about multivariat…
Exact guidance for discrete data improves posterior sampling efficiency.
problem Inefficient guidance for discrete data in posterior sampling.
method Derive exact transition rate for desired distribution given learned discrete flow matching model.
result Significantly improved efficiency with single forward pass per sampling step.