VISR learns controllable features for fast task inference.
problem Generalizing behaviors beyond explicitly learned set for subsequent tasks.
method Combines Successor Features and Variational Inference.
result Achieves human-level performance on 14 Atari games.
MetaVRF learns adaptive kernels for fast few-shot learning.
problem Few-shot learning with limited data.
method MetaVRF with latent variable model and variational inference.
result MetaVRF produces kernels with high representational power and fast adaptation.
Favour speeds up variance estimation in BNNs, making them practical for performance-critical tasks.
problem Slow inference in Bayesian Neural Networks (BNNs) hinders their adoption.
method A fast algorithm for updating a diagonal-plus-low-rank matrix approximation under various operations.
result Favour is as fast as 2-3 inference samples but matches the performance of 10-100 samples.
Paper presents a fast, private MH algorithm for large-scale Bayesian inference.
problem Privacy-preserving Bayesian inference for large-scale data.
method Developed a novel DP-MH algorithm using minibatches.
result First exact and fast DP MH algorithm with privacy, scalability, and efficiency trade-offs.
Efficient algorithm finds fast Transformer models.
problem Slow inference time of Transformer models.
method Decompose Transformer architecture into components, use sampling-based one-shot search.
result Achieved 10% to 30% speedup on pre-trained BERT and 70% on top of a previous state-of-the-art model.
AGMs outperform EGMs in generalizing to unseen inference tasks.
problem Training graphical models for inference tasks not seen during training.
method Adversarial training of an ensemble of discrete graphical models.
result AGMs significantly outperform EGMs in generalization to unseen tasks.
New method for fast inference in diffusion models.
problem Intractable probabilistic inference in diffusion models.
method Variational Gaussian Process, exponential family description, convex optimization.
result Improved fast algorithm for learning model parameters.
Many inference problems in structured prediction are naturally solved by augmenting a tractable dependency structure with complex, non-local auxiliary objectives. This includes the mean field family of variational inference algorithms, soft- or hard-constrained inference using Lagrangian relaxation or linear programmin…
Integrates Fourier features for faster Gaussian process regression.
problem Efficiently scaling Gaussian process regression to large datasets.
method Integrated Fourier features for Gaussian processes.
result Improves Gaussian process regression speed to O(M3) for a broad class of kernels. Sparse Gaussian processes with compact kernels for faster inference.
problem Efficient Gaussian process inference with high computational complexity.
method Parametric families of compactly-supported kernels for sparse matrix representations.
result Sub-quadratic inference complexity and improved performance on real-world tasks.
A new particle algorithm improves mean-field variational inference.
problem Efficiently approximating nonparametric posterior distributions in machine learning.
method Introduces PArticle VI (PAVI), a novel particle-based algorithm for nonparametric mean-field approximation.
result Obtains non-asymptotic error bounds for PArticle VI, providing the first end-to-end guarantee for particle-based MFVI.
DistPred provides a fast, distribution-free method for regression and forecasting.
problem Deterministic point estimates in regression and prediction tasks.
method Transforming proper scoring rules into a differentiable form and using it as a loss function.
result Achieved state-of-the-art performance and significantly improved computational efficiency.
Paper proposes a distributed sampling method for Bayesian inference.
problem Privacy and communication constraints in spatially distributed datasets.
method Alternating Direction Method of Multipliers for distributed sampling.
result Algorithm converges to target distribution in Wasserstein distance.
Density-Regression improves deep uncertainty estimation with faster inference.
problem Efficient uncertainty estimation under distribution shifts with modern deep models.
method Leverages density function for fast inference and distance-aware feature space.
result Density-Regression achieves competitive uncertainty estimation performance.
This paper proposes Relational Similarity Machines (RSM): a fast, accurate, and flexible relational learning framework for supervised and semi-supervised learning tasks. Despite the importance of relational learning, most existing methods are hard to adapt to different settings, due to issues with efficiency, scalabili…
Fast Bayesian inference with adaptable priors for real-time applications.
problem Intractable exact posterior computation limits Bayesian inference's adoption.
method Distribution Transformer architecture that learns mappings between priors and posteriors.
result Significant reduction in computation time from minutes to milliseconds.
Real-time uncertainty estimation for computer vision tasks.
problem Real-time inference of uncertainty in deep learning models.
method Uncertainty-Aware Distribution Distillation method for fast inference.
result Significantly reduced inference time with improved uncertainty and predictive performance.
FAWMF adapts weights for implicit feedback recommendation efficiently.
problem Challenges in treating unobserved data as negative in implicit feedback recommendation.
method FAWMF uses a variational auto-encoder with a parameterized neural network to adaptively assign personalized data confidence weights, and fBGD for efficient learning.
result FAWMF and fBGD outperform existing methods in real-world datasets.
Bayesian REX learns Atari games from demonstrations efficiently.
problem Bayesian reward learning for complex control problems is computationally intractable.
method Bayesian Reward Extrapolation (Bayesian REX) pre-trains a low-dimensional feature encoding and uses preferences to perform fast Bayesian inference.
result Bayesian REX learns Atari games from demonstrations in 5 minutes, competitive with state-of-the-art methods.
New method learns robust meta-representations for fast task adaptation.
problem Transferability of meta-representations in fast adaptation.
method Decoupled encoder-decoder approach with contrastive objective.
result Meta-representations improve downstream performance and noise robustness.
A fast method approximates likelihood scores for noisy linear inverse problems.
problem Solving noisy linear inverse problems efficiently.
method Proposes a simple closed-form approximation to the likelihood score for diffusion and flow-based models.
result Significantly faster than baseline methods while maintaining competitive or better reconstruction performances.
New method speeds up Gaussian process inference for large datasets.
problem Numerical instability and inefficiency in approximate inference methods for non-Gaussian likelihoods.
method Conjugate-computation variational inference with Kalman recursions.
result Linear-time inference with fast and stable variational inference for state-space GP models.
A novel multi-resolution Gaussian process model for efficient time traversal.
problem Inference for long sequences with fast and slow transitions is difficult.
method A novel Gaussian process state-space architecture composed of multiple components, each trained on a different resolution.
result The combined model allows efficient inference for arbitrarily long sequences with complex dynamics.
FAST improves fast and stable task adaptation in DNNs.
problem Catastrophic forgetting in fine-tuned pretrained models.
method Introducing FAST, an easy-to-implement fine-tuning algorithm.
result FAST learns target tasks faster and retains source knowledge longer.
Risk control improves EENNs to make faster predictions without sacrificing accuracy.
problem Determining safe times for EENNs to exit early without degrading performance.
method Adapting risk control frameworks to EENNs to tune their exiting mechanism.
result Risk control enables EENNs to make faster predictions while maintaining user-specified performance goals.
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…
Inference is an integral part of probabilistic topic models, but is often non-trivial to derive an efficient algorithm for a specific model. It is even much more challenging when we want to find a fast inference algorithm which always yields sparse latent representations of documents. In this article, we introduce a si…
In-Place TTT enhances LLMs with dynamic parameter updates at inference time.
problem Static training limits LLMs from adapting to new information.
method In-Place TTT updates a subset of model parameters (fast weights) at inference time.
result In-Place TTT enables 4B-parameter models to outperform on tasks with up to 128k contexts.
VTIRT speeds up IRT inference for dynamic learner proficiency.
problem Expensive and slow inference algorithms for dynamic IRT models.
method Variational Temporal IRT (VTIRT) for fast, accurate inference.
result Orders of magnitude speedup in inference runtime with accurate results.
Sig-DEG speeds up diffusion models by distilling them into faster approximations.
problem Computational intensity of diffusion models at inference time.
method Signature-based differential equation generation to summarize Brownian motion.
result Sig-DEG reduces inference steps by an order of magnitude while maintaining generation quality.
Neural architecture search has been shown to hold great promise towards the automation of deep learning. However in spite of its potential, neural architecture search remains quite costly. To this point, we propose a novel gradient-based framework for efficient architecture search by sharing information across several …
We propose Edward, a Turing-complete probabilistic programming language. Edward defines two compositional representations---random variables and inference. By treating inference as a first class citizen, on a par with modeling, we show that probabilistic programming can be as flexible and computationally efficient as t…
A new inference network learns undirected models from data.
problem Learning undirected models with hidden variables is hard.
method Train a single stochastic inference network from data, using a cost function over queries.
result The network can perform inference tasks like an undirected model without partition function.
Combines PCA and CEM for fast clustering and embedding.
problem Dimensionality and slow EM algorithm convergence for clustering.
method Combines PCA and CEM for simultaneous clustering and data embedding.
result Demonstrates improved clustering and embedding performance.
Over the past decade there has been considerable interest in spectral algorithms for learning Predictive State Representations (PSRs). Spectral algorithms have appealing theoretical guarantees; however, the resulting models do not always perform well on inference tasks in practice. One reason for this behavior is the m…
New loss improves OOD detection without extra data or tuning.
problem Improving OOD detection without additional data or tuning.
method Proposed IsoMax loss and entropic score to replace SoftMax loss.
result Training with IsoMax loss significantly improves OOD detection performance.
CoNBONet improves reliability analysis of complex systems with fast, energy-efficient predictions.
problem Time-dependent reliability analysis of nonlinear systems under stochastic excitations is computationally demanding.
method CoNBONet combines deep operator networks with neuroscience-inspired neuron models for fast, energy-efficient inference.
result CoNBONet provides reliable coverage of failure probabilities with theoretical guarantees.
A new method for few-shot learning using Laplacian regularization.
problem Few-shot learning with limited labeled data.
method Transductive Laplacian-regularized inference for feature embeddings.
result Our method outperforms state-of-the-art methods across various benchmarks.
A new method uses natural gradients for efficient distribution optimization.
problem Challenges in computing natural gradients for many distributions.
method Reframe optimization as a surrogate distribution with easy natural gradient computation.
result Expands set of distributions efficiently targetable with natural gradients.
Paper presents a fast method for estimating hidden states in Bayesian models.
problem Estimating hidden states in Bayesian state space models efficiently.
method Amortized simulation-based inference with pretraining.
result The method achieves sufficient accuracy and fast inference times.
Quantized Variational Inference improves ELBO optimization with fast convergence.
problem Maximizing Evidence Lower Bound (ELBO) for variational inference.
method Optimal Voronoi Tesselation for variance-free gradients, Richardson extrapolation for asymptotic improvement.
result Quantized Variational Inference leads to fast convergence with comparable computational cost.
Effective implementations of sampling-based probabilistic inference often require manually constructed, model-specific proposals. Inspired by recent progresses in meta-learning for training learning agents that can generalize to unseen environments, we propose a meta-learning approach to building effective and generali…
Many real world problems can now be effectively solved using supervised machine learning. A major roadblock is often the lack of an adequate quantity of labeled data for training. A possible solution is to assign the task of labeling data to a crowd, and then infer the true label using aggregation methods. A well-known…
ELM speeds up financial machine learning tasks.
problem Efficiently solving time-sensitive financial tasks with machine learning.
method Single-layer neural networks with random initialization and convex optimization.
result ELM achieves significant computational efficiency in financial applications.
Adaptive workflow combines fast amortized inference with MCMC for many datasets.
problem Trade-off between computational speed and sampling accuracy in Bayesian inference.
method Adaptive workflow integrating amortized inference and MCMC with principled diagnostics.
result Efficiency gains with high posterior quality on tens of thousands of datasets.
Improves sampling speed of ARM models without losing accuracy.
problem Slow sampling from ARMs.
method Predictive sampling algorithm using ARM fixed-point iteration and learned forecasting modules.
result Significant improvements in sampling speed and efficiency.
PRISMA uses PDE residuals for fast, robust, and accurate inference.
problem Slow gradient-based optimization and instability in PDE residual-based methods.
method Integrates PDE residuals directly into the model's architecture via attention mechanisms in the spectral domain.
result Competitive accuracy with significantly lower inference costs and faster speeds.
A new Gaussian process framework uses neural feature maps for scalable, accurate inference.
problem Efficient and accurate Gaussian process inference for diverse data types.
method Neural feature maps to construct expressive kernels, with theoretical guarantees and practical scalability.
result The approach outperforms existing methods in accuracy and efficiency across various data modalities.