PointPillars improves object detection speed and accuracy in point clouds.
problem Encoding point clouds for efficient object detection.
method PointPillars uses PointNets to learn pillar representations of point clouds, combined with a lean downstream network.
result PointPillars outperforms previous encoders in both speed and accuracy.
A fast graph embedding method for large graphs.
problem Efficiently embedding large graphs for various applications.
method One-hot graph encoder embedding with linear complexity.
result Graph encoder embedding is approximately normally distributed and converges to its mean.
Efficiently accelerates attention calculation for Transformers with relative positional encoding.
problem Quadratic complexity of attention in long sequences.
method Kernelized attention with Fast Fourier Transform (FFT) for RPE.
result Achieves O(n log n) time complexity, mitigates training instability, and outperforms other models.
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.
Transmeter quickly measures transferability between different datasets.
problem Measuring transferability between heterogeneous multivariate datasets.
method Pre-trained source model, adversarial network, and encoder-decoder architecture.
result Transmeter provides the most accurate transferability measurement up to 10.3 times faster.
Method finds reference products for a given item.
problem Finding relevant products for a given item.
method Product representation learning and fingerprint-type vector searching.
result The method outperforms peer services in search return rate and precision.
A new method for target propagation using iterative approximations converges fast and is more biologically plausible.
problem Improving target propagation methods for neural networks.
method Iterative approximate inverses and local auto-encoders.
result The method converges exponentially fast under certain conditions.
New methods encode high-cardinality string variables efficiently.
problem Efficient encoding of high-cardinality string categorical variables.
method Two approaches: Gamma-Poisson matrix factorization and min-hash encoder.
result Improves supervised learning with high-cardinality categorical variables.
Auto-encoding is an important task which is typically realized by deep neural networks (DNNs) such as convolutional neural networks (CNN). In this paper, we propose EncoderForest (abbrv. eForest), the first tree ensemble based auto-encoder. We present a procedure for enabling forests to do backward reconstruction by ut…
We present the Video Ladder Network (VLN) for efficiently generating future video frames. VLN is a neural encoder-decoder model augmented at all layers by both recurrent and feedforward lateral connections. At each layer, these connections form a lateral recurrent residual block, where the feedforward connection repres…
We build on auto-encoding sequential Monte Carlo (AESMC): a method for model and proposal learning based on maximizing the lower bound to the log marginal likelihood in a broad family of structured probabilistic models. Our approach relies on the efficiency of sequential Monte Carlo (SMC) for performing inference in st…
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.
TiDE uses MLP for fast, simple long-term time-series forecasting.
problem Long-term time-series forecasting challenges.
method Time-series Dense Encoder (TiDE) based on MLP.
result TiDE matches or outperforms Transformer models while being 5-10x faster.
This work presents a novel objective function for the unsupervised training of neural network sentence encoders. It exploits signals from paragraph-level discourse coherence to train these models to understand text. Our objective is purely discriminative, allowing us to train models many times faster than was possible …
LD-EnSF speeds up data assimilation with sparse observations.
problem Efficiently assimilate sparse and noisy data into complex dynamical systems.
method LD-EnSF uses latent dynamics networks and history-aware LSTM encoders to process sparse observations without full-space simulations.
result Achieves significant speedups over existing methods while maintaining high accuracy.
New method uses neural networks to interpolate stellar atmospheres with high precision.
problem Recover precise stellar model atmospheres from grids of models.
method Deep neural network with 1D convolutional auto-encoder for feature extraction.
result Higher precision compared to traditional methods.
We study the problem of learning latent variables in Gaussian graphical models. Existing methods for this problem assume that the precision matrix of the observed variables is the superposition of a sparse and a low-rank component. In this paper, we focus on the estimation of the low-rank component, which encodes the e…
This paper deals with two related problems, namely distance-preserving binary embeddings and quantization for compressed sensing . First, we propose fast methods to replace points from a subset X⊂Rn, associated with the Euclidean metric, with points in the cube {±1}m and we associa…
A fast method finds interpretable counterfactual explanations using class prototypes.
problem Finding understandable counterfactual explanations for classifier predictions.
method Using class prototypes, the method speeds up and improves interpretability of counterfactual instances.
result The method significantly speeds up and improves the interpretability of counterfactual explanations.
BLISS detects and separates astronomical sources quickly and accurately.
problem Detecting and separating overlapping astronomical sources in large images.
method Bayesian Light Source Separator (BLISS) using deep generative models and variational inference.
result BLISS can process megapixel images in seconds and produce highly accurate catalogs.
New method learns nonlinear projections for reduced-order modeling of complex dynamical systems.
problem Modeling transient dynamics near a manifold in nonlinear systems.
method Constrained autoencoder neural networks with invertible activation functions and biorthogonal weight matrices.
result Demonstrated effectiveness on a vortex shedding model, learning oblique fibers for fast dynamics.
Automatically learns efficient algorithms for structured transforms like FFT.
problem Efficient algorithms for structured linear transforms.
method Generic parameterization of divide-and-conquer methods.
result Reproduces Cooley-Tukey FFT algorithm to machine precision.
Tutorial on using neural networks for single cell data analysis.
problem Handling large sequencing datasets efficiently.
method Single cell variational inference using variational auto-encoder.
result Model learns data distribution for insights.
Auto-encoders learn atomistic to coarse-grained mappings for molecular dynamics.
problem Simulating large systems in molecular dynamics is computationally expensive.
method Auto-encoders learn both atomistic to coarse-grained mappings and the coarse-grained potential energy function.
result Auto-encoders enable efficient simulation of larger systems in molecular dynamics.
We consider the problem of efficiently approximating and encoding high-dimensional data sampled from a probability distribution ρ in RD, that is nearly supported on a d-dimensional set M - for example supported on a d-dimensional Riemannian manifold. Geometric Multi-Resolution Analysis (GM…
DRNets combine deep learning and reasoning for complex tasks.
problem Solving complex tasks, especially in scientific discovery, with limited supervision.
method DRNets integrate logic and neural network optimization to encode structured latent spaces constrained by prior knowledge.
result DRNets outperform state-of-the-art models in scientific discovery tasks, recovering more precise crystal structures.
We present a new paradigm for speeding up randomized computations of several frequently used functions in machine learning. In particular, our paradigm can be applied for improving computations of kernels based on random embeddings. Above that, the presented framework covers multivariate randomized functions. As a bypr…
PhyloVAE learns tree topologies without supervision.
problem Learning accurate tree representations from evolutionary data.
method Unsupervised learning via variational autoencoders with efficient tree generation.
result PhyloVAE generates high-resolution tree topologies efficiently.
CSLVAE generates large chemical libraries efficiently.
problem Navigating ultra-large combinatorial synthesis libraries.
method Hierarchically-organized database with molecular encoder and decoder.
result Generates valid molecular graphs without autoregression.
We present a comprehensive framework for structured sparse coding and modeling extending the recent ideas of using learnable fast regressors to approximate exact sparse codes. For this purpose, we develop a novel block-coordinate proximal splitting method for the iterative solution of hierarchical sparse coding problem…
New bounds enable training of probabilistic models for deep networks.
problem Training scalable latent variable models for deep networks.
method Introducing new variational bounds for specific output layers of neural networks.
result Analytical bounds for certain output layers allow training without re-parameterization or Monte Carlo approximations.
The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the reliance on huge amounts of labeled data and specialized hardware can be a limiti…
FastSGT improves accuracy in BERT-based DST for SGD datasets.
problem Dialog State Tracking in goal-oriented dialogue systems.
method BERT-based model with two carry-over procedures and multi-head attention.
result Significantly improved accuracy compared to baseline model.
FasterVoiceGrad speeds up VC by 6-7x with novel distillation.
problem Slow iterative sampling in diffusion-based VC models.
method Adversarial diffusion conversion distillation (ADCD) to create a faster one-step model.
result 6.6-6.9 and 1.8x faster on GPU and CPU, respectively.
New hashing method improves document retrieval precision.
problem Efficiently retrieving similar documents from large text databases.
method Pairwise supervised hashing with Bernoulli VAE and unbiased gradient estimator.
result Superior performance compared to existing methods.
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.
We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable t…
RNA-binding proteins (RBPs) play crucial roles in many biological processes, e.g. gene regulation. Computational identification of RBP binding sites on RNAs are urgently needed. In particular, RBPs bind to RNAs by recognizing sequence motifs. Thus, fast locating those motifs on RNA sequences is crucial and time-efficie…
In many domains, scientists build complex simulators of natural phenomena that encode their hypotheses about the underlying processes. These simulators can be deterministic or stochastic, fast or slow, constrained or unconstrained, and so on. Optimizing the simulators with respect to a set of parameter values is common…
Learning attribute applicability of products in the Amazon catalog (e.g., predicting that a shoe should have a value for size, but not for battery-type at scale is a challenge. The need for an interpretable model is contingent on (1) the lack of ground truth training data, (2) the need to utilise prior information abou…
This research improves dynamical systems understanding by identifying latent states and their nonlinear transitions.
problem Previous work on dynamical systems could not identify nonlinear transition dynamics, leading to unreliable predictions.
method Proposes a state-space modeling framework using variational auto-encoders to identify latent states and their nonlinear transition functions.
result Demonstrates high accuracy in recovering latent state dynamics and future prediction accuracy.
Jointly learns encoding and decoding for noisy channels.
problem Asymptotic optimality of source and channel separation in finite bit-length regimes.
method Discrete variational autoencoder model with noise simulation.
result Jointly learned codes are competitive and learn robust representations.
A new method improves RVFL networks for resource-efficient machine learning.
problem Deploying machine learning on edge devices with limited resources.
method Density encoding and hyperdimensional computing operations.
result The proposed method achieves higher accuracy and lower energy consumption.
Deep reinforcement learning (deep RL) has been successful in learning sophisticated behaviors automatically; however, the learning process requires a huge number of trials. In contrast, animals can learn new tasks in just a few trials, benefiting from their prior knowledge about the world. This paper seeks to bridge th…
New deep learning model estimates scattering timescale of FRBs efficiently.
problem Estimating scattering timescale of fast radio bursts (FRBs) is a bottleneck.
method Multimodal Transformer Based Generic Mixture Density Network (MT-GMDN) that ingests dynamic spectrum and timeseries profile.
result Achieves 94% R2 on expected value of τ for measurable scattering. 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.
A new model reconciles rough volatility and jumps.
problem Combining rough volatility and jump processes.
method Developed a reversionary Heston model with fast mean reversions and large vol-of-vols.
result The reversionary Heston model converges to Lévy jump processes for certain values of the parameter.
The paper offers error bounds for quantized dynamical models.
problem Accuracy of dynamical models from dependent data sequences.
method Developed uniform error bounds for quantized models and imperfect optimization algorithms.
result Unified bounds for slow and fast rates, scaling with model encoding bits.