Large language models can't efficiently reason conditionally in a distribution-free setting.
problem Impossibility of conditional PAC-efficient reasoning in large language models.
method Proof of impossibility in a distribution-free setting for non-atomic input spaces.
result Any algorithm achieving conditional PAC efficiency must defer to the expert model with high probability.
Woodbury transformations improve deep generative models with efficient invertibility and determinant calculation.
problem Efficiently invertible and determinant-calculable functions for deep generative models.
method Introducing Woodbury transformations that leverage matrix identities for efficient invertibility and determinant calculation.
result Woodbury transformations enable high-dimensional interactions, efficient sampling, and likelihood evaluation, outperforming other flow architectures.
The paper discusses the limitations of efficiency metrics in machine learning models.
problem Inadequate reporting of efficiency metrics leads to incomplete conclusions.
method Thoroughly discusses common cost indicators, their advantages and disadvantages, and how they contradict each other.
result Incomplete reporting of efficiency metrics can lead to partial conclusions and a blurred picture of model practical considerations.
Improved sample efficiency in reinforcement learning with deep Gaussian processes.
problem Efficiently learn to control actions with limited interaction data.
method Deep Gaussian processes that simulate dynamics with depth and prior knowledge.
result Significantly improved early sample efficiency across various tasks, including half-cheetah control.
Paper proposes efficient optimizers for large language models with fast convergence and low memory usage.
problem Designing efficient optimizers for large language models with low-memory requirements and fast convergence.
method Structured Fisher information matrix approximation and low-rank extension framework.
result New optimizers (RACS and Alice) achieve better convergence and lower memory usage than existing methods.
Deep networks can approximate score functions in high-dimensional graphical models efficiently.
problem Approximation efficiency of score functions by deep neural networks in high-dimensional graphical models like Markov random fields.
method Variational inference denoising algorithms and efficient neural network representation.
result Efficient sample complexity bound for diffusion-based generative modeling when score functions are learned by deep neural networks.
This paper investigates efficient Transformers and finds they scale with problem size.
problem Finding suitable replacements for standard Transformers in large-scale tasks.
method Modeling efficient Transformers (Sparse and Linear) as Dynamic Programming problems and analyzing their reasoning capabilities.
result Efficient Transformers scale with problem size, but can be more efficient for certain DP problems.
FastFID efficiently trains generative models with FID loss.
problem Efficiently training generative models with FID loss.
method Introduces FastFID to train generative models with FID as a loss function.
result Improves FID for GANs using FID as an additional loss.
ASEs use surrogate estimation to efficiently evaluate model performance with minimal labels.
problem Efficient model evaluation with limited labels.
method Surrogate-based estimation and active learning.
result ASEs offer greater label-efficiency than current methods for deep neural networks.
New SMC sampler improves diffusion model sampling efficiency.
problem Sampling generative diffusion models efficiently.
method Constructs correlated observation paths and designs a sampler.
result Improved statistical efficiency, especially under outlier conditions.
Unified Bayesian Optimization framework for model selection balancing effectiveness and training efficiency.
problem Balancing model effectiveness and training efficiency in machine learning model selection.
method Proposes a unified Bayesian Optimization framework to jointly optimize model effectiveness and training efficiency.
result Models selected using the proposed framework significantly improve training efficiency while maintaining strong effectiveness.
A new Hopfield model reduces inefficiency in large transformer models.
problem Inefficiency in training large transformer-based models.
method Introduces an Outlier-Efficient Hopfield Model (OutEffHop) to improve model performance.
result Achieves up to 26% reduction in model output norms across four models.
Proposes a new approach to approximate maximum likelihood for complex models.
problem Intractable likelihood functions in complex parametric models.
method Simulation-based constrained approximation to the structural model.
result Estimators nearly as efficient as maximum likelihood, feasible in many cases.
Efficient method for lookback option pricing under Markov models.
problem Pricing lookback options under Markov models.
method Model-free representations combined with numerical quadrature and Markov chain approximation.
result Efficient method applicable to various Markov models.
Examines learning efficiency in neural networks and related models.
problem Analyzing efficiency in deep learning models with singular learning coefficients.
method Examined learning coefficients in neural networks and three-layer neural networks with ReLU units.
result Extended results to include Softmax function, providing a broader understanding of learning efficiency.
Study introduces a variational approach for efficient KL divergence estimation in Dirichlet mixture models.
problem Efficient estimation of KL divergence in Dirichlet mixture models.
method Variational approach for a closed-form solution.
result Superior efficiency and accuracy compared to Monte Carlo methods.
Efficient exploration improves large language model performance with fewer queries.
problem Improving large language model performance with fewer human feedback queries.
method Sequentially generates queries, fits a reward model to feedback, uses double Thompson sampling with epistemic neural network uncertainty.
result Efficient exploration enables high performance with far fewer queries.
Improved method for efficient black-box optimization in latent space.
problem Efficiently optimize expensive black-box functions over complex input spaces.
method Optimize in latent space of deep generative models, retrain model periodically and weight data points.
result Significantly improved efficiency and performance on synthetic and real-world problems.
P-Trees improve investment performance by optimizing the efficient frontier.
problem Optimizing investment performance in complex financial markets.
method Introducing P-Trees, a new tree-based model for analyzing panel data.
result P-Trees significantly advance the efficient frontier and outperform existing models.
Bayesian model for energy-efficient EV navigation.
problem Limited battery capacity in electric vehicles.
method Bayesian modeling and online learning framework with exploration strategies.
result Established rigorous regret bounds for Thompson Sampling.
FisherSFT selects informative examples to fine-tune LLMs efficiently.
problem Adapting large language models to new domains efficiently.
method Selects examples maximizing information gain using Hessian of log-likelihood.
result Empirically demonstrates improved performance with reduced computational cost.
BREMEN optimizes policies offline with fewer data, achieving efficient deployment.
problem High cost of updating policies in real-world applications.
method Behavior-Regularized Model-ENsemble (BREMEN) algorithm for offline optimization.
result BREMEN achieves impressive deployment efficiency with 5-10 deployments, outperforming standard RL methods.
KalMamba improves RL efficiency with probabilistic SSMs.
problem Efficiency in learning and inference for probabilistic SSMs in RL.
method Combines Mamba's scalability with Kalman filtering for efficient probabilistic SSMs.
result KalMamba outperforms state-of-the-art SSMs in RL, especially on longer sequences.
Unified model for market dynamics, linking price and order flow.
problem Modeling market dynamics and order flow in a unified framework.
method Markovian market model driven by a hidden Brownian efficient price, signal-driven and queue-reactive models.
result Stability of mid-price around efficient price at macroscopic scale, behavior as diffusion.
GP-TS optimizes TLM pre-training hyperparameters efficiently.
problem Resource inefficiency in TLM pre-training.
method Bayesian optimization with Thompson sampling and Gaussian process.
result GP-TS achieves lower MLM loss in fewer epochs.
XSPNs combine SPNs and MEVMs for efficient inference in data with repeated parts.
problem Efficient inference in data with repeated interchangeable parts.
method Introducing Exchangeability-Aware Sum-Product Networks (XSPNs) that combine SPNs and MEVMs.
result XSPNs can be more accurate than conventional SPNs when data contains repeated parts.
Efficient diffusion model for symmetric manifolds reduces training and computation costs.
problem Heat kernel computations for manifold diffusion models are computationally expensive and infeasible.
method Spatially-varying covariance diffusion model, efficient objective derived via Ito's Lemma.
result Our model reduces training time and arithmetic operations by orders of magnitude.
Collaborative filtering, especially latent factor model, has been popularly used in personalized recommendation. Latent factor model aims to learn user and item latent factors from user-item historic behaviors. To apply it into real big data scenarios, efficiency becomes the first concern, including offline model train…
GLASS Flows improves flow and diffusion model performance by optimizing sampling efficiency.
problem Efficiency bottleneck in sampling Markov transitions for flow and diffusion models.
method Introduces GLASS Flows, a new sampling paradigm that simulates a 'flow matching model within a flow matching model' to sample Markov transitions efficiently.
result Eliminates the trade-off between stochastic evolution and efficiency in large-scale text-to-image models.
Cardinality potentials are a generally useful class of high order potential that affect probabilities based on how many of D binary variables are active. Maximum a posteriori (MAP) inference for cardinality potential models is well-understood, with efficient computations taking O(DlogD) time. Yet efficient marginalizat…
Study efficient auditing of ML fairness models.
problem Scalability of auditing ML models for fairness.
method Query-based auditing algorithms for estimating demographic parity.
result Optimal deterministic and practical randomized algorithms for fairness estimation.
Proposes DGCN with trajectory sampling for data-efficient policy search in MBRL.
problem Improving data efficiency in model-based reinforcement learning.
method Combines trajectory sampling and DGCN for uncertainty propagation in probabilistic world models.
result Improves sample-efficiency over other uncertainty propagation methods and probabilistic models.
Efficiently approximates higher-order derivatives for generative models.
problem Expensive computation of higher-order derivatives in generative models.
method Rewrite SM objective in terms of directional derivatives and use finite difference for efficient approximation.
result Comparable results to gradient-based methods but significantly more computationally efficient.
An investor faced with a contingent claim may eliminate risk by perfect hedging, but as it is often quite expensive, he seeks partial hedging (quantile hedging or efficient hedging) that requires less capital and reduces the risk. Efficient hedging for European call option was considered in the standard Black-Scholes m…
Efficiently transforms samples from various statistical models.
problem Approximately transforming samples from one statistical model to another without knowing the source model's parameters.
method Constructs computationally efficient procedures to reduce uniform, Erlang, and Laplace models to general target families.
result Establishes nonasymptotic reductions between canonical high-dimensional problems, such as mixtures of experts, phase retrieval, and signal denoising.
Improves sample efficiency in RL by matching model-based gradients.
problem Lack of sample efficiency in model-free RL.
method Gradient matching between model-based and model-free RL components.
result Improves sample efficiency without increasing asymptotic bias.
FiT combines transfer and meta-learning for efficient few-shot image classification.
problem Few-shot image classification in personalized and federated learning settings.
method Combines transfer learning and meta-learning with fixed pretrained backbones and fine-tuned FiLM adapter layers.
result Achieves state-of-the-art accuracy on VTAB-1k benchmark with fewer than 1% of updateable parameters.
Study finds super-efficiency correlates more strongly with stock market valuation than ROA in Chinese banks.
problem Investigating the relationship between bank efficiency and stock market valuation.
method Employed a non-radial, non-oriented slack-based super-efficiency Data Envelopment Analysis (Super-SBM-UND-VRS) model, treating NPLs as undesired output.
result Super-efficiency is more strongly correlated with stock market valuation than ROA, as measured by Tobin's Q.
CoLoRA leverages task similarity to boost fine-tuning efficiency.
problem Efficiently fine-tuning large foundation models with scarce labeled data.
method CoLoRA trains a shared adapter for task similarity and personalized adapters for user-specific tasks.
result CoLoRA significantly boosts fine-tuning performance when tasks are similar.
Theoretical analysis shows MDMs can be efficient but not for all metrics.
problem Understanding the efficiency-accuracy trade-off of diffusion language models.
method Theoretical analysis of Masked Diffusion Model (MDM) using perplexity and sequence error rate as metrics.
result MDM achieves near-optimal perplexity but requires linear scaling for sequence error rate, highlighting efficiency-accuracy trade-offs.
HeteroFL trains diverse clients with varying capabilities efficiently.
problem Training models on clients with different computational and communication capacities.
method Proposes HeteroFL framework to adaptively distribute subnetworks based on client capabilities.
result Adaptive subnetwork distribution leads to efficient computation and communication.
A new diffusion model uses efficient conditional estimators for discrete data.
problem Efficient estimation of conditional probabilities for discrete data.
method Discrete denoising diffusion framework with sample-efficient NeurISE conditional estimation.
result The method outperforms existing approaches in various metrics on binary and scientific data.
GEnBP combines EnKF and GaBP for efficient high-dimensional inference.
problem Efficient inference in high-dimensional models.
method Gaussian Ensemble Belief Propagation algorithm combining EnKF and GaBP.
result GEnBP outperforms existing methods in accuracy and efficiency.
The Hull-White one factor model is used to price interest rate options. The parameters of the model are often calibrated to simple liquid instruments, in particular European swaptions. It is therefore very important to have very efficient pricing formula for simple instruments. Such a formula is proposed here for Europ…
Gaussianization flows transform any random vector into a Gaussian, enabling efficient computation and sample generation.
problem Transforming any random vector into a Gaussian for efficient computation and sample generation.
method Iterative Gaussianization and normalizing flow model.
result Gaussianization flows are universal approximators and achieve better performance on tabular datasets.
Paper proposes an EKF for estimating time-varying market efficiency.
problem Estimating time-varying market efficiency under nonlinear dynamics.
method Extended Kalman Filter (EKF) for time-varying autoregressive models.
result U.S. market generally remained weak-form efficient since mid-1946.
Improves diffusion model performance and efficiency through classical search.
problem Tackles inference-time control in diffusion models.
method Proposes a framework combining local and global search for efficient navigation.
result Significant gains in performance and efficiency across various domains.
Unified scoring model improves efficiency and performance across multiple tasks.
problem Efficient and resource-efficient automated scoring for diverse tasks.
method Knowledge-distilled multi-task Mixture-of-Experts (MoE) approach.
result Comparable performance to task-specific models with significantly less storage and training resources.