SLHF uses sequential game theory to optimize preferences from human feedback.
problem Optimizing preferences from human feedback in sequential settings.
method SLHF frames the problem as a sequential-move game between Leader and Follower, decomposing the optimization into refinement and adversarial optimization.
result SLHF achieves strong alignment across diverse preference datasets and scales to large models.
A novel framework refines diffusion models iteratively for better downstream reward optimization.
problem Optimizing reward functions during inference of diffusion models.
method Iterative refinement process with noising and reward-guided denoising steps.
result Superior empirical performance in protein and DNA design.
Develops a new framework for analyzing sequential decision-making problems using information theory.
problem Lack of information-theoretic generalization bounds for sequential decision-making problems.
method Introduces a sequential supersample framework that separates learner filtration from proof-side enlargement, controlling the generalization gap by sequential CMI.
result Establishes a sequential CMI that controls the generalization gap in sequential decision-making problems.
PG-EVIKAL refines molecular property predictions using neighbor fusion and evidential neural networks.
problem Improving molecular property predictions using test-time neighbor fusion.
method Adapting evidential neural networks to refine predictions by re-ranking structurally similar neighbors.
result PG-EVIKAL reduces RMSE on 14 out of 16 molecular datasets, improving calibration and sequential refinement.
Bayesian method refines surrogate models for accurate full waveform inversion.
problem Complex input/output relations in full waveform inversion make accurate surrogate models difficult.
method Iterative refinement of surrogate models using MCMC samples and progressively expanding frequency bandwidth.
result Highly accurate surrogate model across full bandwidth enables accurate final MCMC inversion.
Optimal timing strategy for mean-reverting price spreads.
problem Trading price spreads with mean-reverting characteristics.
method Sequential optimal stopping framework with refined signature method.
result Precise entry and exit timings that maximize gains.
Self-distillation improves constrained language generation by aligning models with target distributions.
problem Sparse and uninformative reward signals in constrained generation settings.
method Iteratively refining the base model through self-distillation, incorporating learned twist functions and proposals.
result Substantial gains in generation quality through improved model alignment with target distributions.
A new method for estimating large-scale linear models with improved precision.
problem Estimating large-scale linear statistical models efficiently.
method Sequential Least-Squares Estimators with Fast Randomized Sketching (SLSE-FRS), integrating Sketch-and-Solve and Iterative-Sketching methods.
result SLSE-FRS produces high-precision estimators, outperforming state-of-the-art methods.
This paper tackles sequential distribution shifts in representation learning.
problem Learning meaningful representations in a sequence of distribution shifts.
method Nonlinear Independent Component Analysis (ICA) framework for continual causal representation learning.
result The method achieves performance comparable to joint training on multiple offline distributions and shows no benefit from the incoming new distribution on all latent variables.
We connect a broad class of generative models through their shared reliance on sequential decision making. Motivated by this view, we develop extensions to an existing model, and then explore the idea further in the context of data imputation -- perhaps the simplest setting in which to investigate the relation between …
MGDL refines deep neural networks by training grades sequentially, improving stability.
problem Training deep neural networks is challenging due to nonconvex optimization landscapes.
method MGDL trains deep networks grade by grade, freezing previously learned grades and training new ones to fit residuals.
result MGDL guarantees vanishing error in a fixed-width multigrade ReLU architecture.
Recent advances in bandit tools and techniques for sequential learning are steadily enabling new applications and are promising the resolution of a range of challenging related problems. We study the game tree search problem, where the goal is to quickly identify the optimal move in a given game tree by sequentially sa…
Sharp privacy bounds for sequential analysis of sensitive data.
problem Privacy degradation under sequential analysis of sensitive data.
method Edgeworth expansion in f-differential privacy framework.
result Improved privacy bounds under composition with refined approximation accuracy.
The design of multiple experiments is commonly undertaken via suboptimal strategies, such as batch (open-loop) design that omits feedback or greedy (myopic) design that does not account for future effects. This paper introduces new strategies for the optimal design of sequential experiments. First, we rigorously formul…
Improved state estimation in high-dimensional models using Zig-Zag Sampler.
problem Weight degeneracy in particle filtering methods for high-dimensional state space models.
method Discrete Zig-Zag Sampler applied within the Composite MH Kernel of SMCMC framework.
result Improves estimation accuracy and increases acceptance ratio in high-dimensional state estimation.
We present a representation learning algorithm that learns a low-dimensional latent dynamical system from high-dimensional \textit{sequential} raw data, e.g., video. The framework builds upon recent advances in amortized inference methods that use both an inference network and a refinement procedure to output samples f…
This paper is devoted to the study of the max K-armed bandit problem, which consists in sequentially allocating resources in order to detect extreme values. Our contribution is twofold. We first significantly refine the analysis of the ExtremeHunter algorithm carried out in Carpentier and Valko (2014), and next propose…
WaveGrad generates high-fidelity audio using gradient estimation.
problem Generating high-fidelity audio efficiently.
method Conditional model using score matching and diffusion models, iteratively refining a Gaussian white noise signal.
result WaveGrad can generate high-fidelity audio samples using as few as six iterations.
Diffusion models generate music sequences without autoregressive loops.
problem Generating music sequences from symbolic data using diffusion models.
method Parameterize discrete symbolic data in continuous latent space, train diffusion model, generate sequences through reverse process.
result Strong unconditional generation and post-hoc conditional infilling compared to autoregressive models.
We propose a new approach to solve optimal stopping problems via simulation. Working within the backward dynamic programming/Snell envelope framework, we augment the methodology of Longstaff-Schwartz that focuses on approximating the stopping strategy. Namely, we introduce adaptive generation of the stochastic grids an…
Learning the minimum/maximum mean among a finite set of distributions is a fundamental sub-task in planning, game tree search and reinforcement learning. We formalize this learning task as the problem of sequentially testing how the minimum mean among a finite set of distributions compares to a given threshold. We deve…
Additive Gaussian process framework handles monotonicity constraints in high dimensions.
problem Handling monotonicity constraints in high-dimensional data.
method Additive Gaussian process framework with MaxMod algorithm for dimension reduction.
result Framework enables to satisfy monotonicity constraints everywhere in the input space.
NARD extends ARD for linear models, promoting sparsity and correlation structure.
problem Sparse relationships between inputs and outputs, capturing correlation structure.
method Matrix normal prior with sparsity-inducing parameter, iterative updates, sequential evaluation, and surrogate function approximation.
result Significant computational efficiency improvements with comparable performance.
New algorithm tackles stochastic optimization with inequality constraints.
problem Stochastic optimization with inequality constraints in various applications.
method Active-set stochastic sequential quadratic programming (StoSQP) with a differentiable exact augmented Lagrangian.
result Global convergence for any initialization, KKT residuals converge to zero almost surely.
Algorithm captures and refines features for efficient lifelong learning.
problem Efficiently learning multiple tasks sequentially with limited data.
method Proposes a lifelong learning algorithm that maintains and refines internal feature representation.
result Proves sample complexity improvement and matches lower bound for efficiency.
As we show using the notion of equilibrium in the theory of infinite sequential games, bubbles and escalations are rational for economic and environmental agents, who believe in an infinite world. This goes against a vision of a self regulating, wise and pacific economy in equilibrium. In other words, in this context, …
Proposes a new model for online anomaly detection in multivariate time series.
problem Inaccurate anomaly detection in multivariate time series due to spurious correlations and lack of temporal causality.
method Clusters channels based on correlations, embeds each cluster, and integrates information through a causal mixer while maintaining temporal causality.
result Consistently superior performance across six public benchmark datasets.
A new sampling strategy improves reliability and robustness optimization for complex designs.
problem High sample requirements for optimizing reliability and robustness in complex designs.
method Local Latin Hypercube Refinement (LoLHR) for multi-objective design uncertainty optimization.
result LoLHR achieves better results compared to other surrogate-based strategies.
A new particle filter uses diffusion models to improve state estimation from noisy data.
problem Sequentially estimating the state of a dynamical system from noisy and incomplete observations.
method Uses a diffusion model to simulate and predict system dynamics, incorporating noisy observations to refine predicted states.
result An unbiased particle filtering method that rigorously fuses observational data with diffusion model simulations.
A new UCB algorithm for heavy-tailed bandits with near-optimal regret.
problem Sequential decision making in uncertain environments with heavy-tailed rewards.
method Data-driven, distribution-free UCB algorithm combining resampled median-of-means and UCB.
result Near-optimal regret bound for heavy-tailed distributions.
Pareto optimal centralized risk sharing with multiple agents
problem Centralized risk sharing with endogenous prices
method Inclusive and fair Pareto optimality
result Equivalence between inclusive and fair Pareto optimality and balanced sequential optimization
It is now much easier than ever before to produce videos. While the ubiquitous video data is a great source for information discovery and extraction, the computational challenges are unparalleled. Automatically summarizing the videos has become a substantial need for browsing, searching, and indexing visual content. Th…
A novel CAB-XDE framework predicts speculative stock prices with high accuracy.
problem Forecasting speculative stock prices in volatile markets.
method Customized attention BiLSTM with XGBoost, integrating attention mechanism and weight determination theory-error reciprocal method.
result Empirically validated with MAPE of 0.0037, MAE of 84.40, and RMSE of 106.14.
Most existing text-to-image synthesis tasks are static single-turn generation, based on pre-defined textual descriptions of images. To explore more practical and interactive real-life applications, we introduce a new task - Interactive Image Editing, where users can guide an agent to edit images via multi-turn textual …
AIHT improves online high-dimensional quantile regression by separating support discovery and refinement.
problem Online high-dimensional quantile regression with structural sparsity.
method Adaptive Iterative Hard Thresholding (AIHT) alternates stochastic updates with adaptive hard-thresholding steps.
result AIHT achieves logarithmic regret for the sliding-window objective in high-dimensional settings.
Annealed Entropic Allocation improves ranking and selection by mitigating hard switching and improving finite-budget discrimination.
problem Sequential budget allocation in ranking and selection
method Annealed weighted soft-min framework
result Surrogate converges uniformly to the hard minimum, soft-min weights concentrate on active challengers, and target allocation map is continuous.
We consider the problem of transfer learning in an online setting. Different tasks are presented sequentially and processed by a within-task algorithm. We propose a lifelong learning strategy which refines the underlying data representation used by the within-task algorithm, thereby transferring information from one ta…
Study efficient sequential evaluation of large language models using historical data.
problem Sequentially evaluate a new large language model (LLM) on a fixed question set.
method Construct a confidence sequence (CS) and design active querying rules to shrink CS width.
result Simple uniform sampling can sometimes outperform adaptive querying rules.
Algorithm identifies optimal stable matching in uncertain two-sided markets.
problem Sequential learning in two-sided markets with unknown preferences.
method Pure exploration approach with elimination-based algorithms exploiting partial preference information.
result Identification of pervasive stable matching for optimal stable matching identification.
We develop a multilevel approach to compute approximate solutions to backward differential equations (BSDEs). The fully implementable algorithm of our multilevel scheme constructs sequential martingale control variates along a sequence of refining time-grids to reduce statistical approximation errors in an adaptive and…
Adaptive sampling results in dramatic improvements in the recovery of sparse signals in white Gaussian noise. A sequential adaptive sampling-and-refinement procedure called Distilled Sensing (DS) is proposed and analyzed. DS is a form of multi-stage experimental design and testing. Because of the adaptive nature of the…
Improved bounds for unbounded losses using transductive priors.
problem Sequential regression and classification with unbounded losses.
method Exponential weights algorithm with transductive priors.
result Statistical bounds independent of design vectors and optimal solution norm.
We study the problem of building generative models of natural source code (NSC); that is, source code written and understood by humans. Our primary contribution is to describe a family of generative models for NSC that have three key properties: First, they incorporate both sequential and hierarchical structure. Second…
A new method estimates rare failure events in complex systems.
problem Estimating the probability of rare failure events in non-linear systems.
method Stochastic Spectral Embedding (SSE) combined with modifications for efficient rare event estimation.
result Rare failure probability decomposed into conditional probabilities for easier computation.
AF improves classification models by adaptively weighting trees.
problem Improving classification model performance.
method AF combines OP2T for input-dependent weights and MIO for dynamic refinement.
result AF consistently outperforms RF, XGBoost, and other weighted RF.
New inequality for refined knot invariants in a specific space.
problem General adjunction inequality for refined s-invariants does not hold. method Introduced an adjunction inequality for a specific spatial refinement in kCP2. result An adjunction inequality holds for the s-version of the Sq1-refinement in kCP2. We study refined topological string theory in the presence of orientifolds by counting second-quantized BPS states in M-theory. This leads us to propose a new integrality condition for both refined and unrefined topological strings when orientifolds are present. We define the SO(2N) refined Chern-Simons theory which co…
Refines neural network predictions using background knowledge for improved accuracy.
problem Compensate for lack of labeled data in neural networks.
method Introduces differentiable refinement functions and Iterative Local Refinement (ILR) algorithm to refine predictions efficiently and accurately.
result ILR finds competitive results in MNIST addition task and refines predictions on complex SAT formulas.