Paper proposes IABF to improve NECST robustness.
problem Limited robustness of NECST learned coding networks.
method Infomax Adversarial-Bit-Flip (IABF) to improve stability and robustness.
result IABF achieves state-of-the-art performances on compression and error correction benchmarks.
DeepJSCC-f uses feedback to improve image transmission quality.
problem Improve image transmission quality in feedback channels.
method Autoencoder-based joint source-channel coding (DeepJSCC-f) exploiting feedback.
result Improves reconstruction quality for fixed-length or variable-length transmission.
Deep JSCC maps images directly to channel symbols for wireless transmission.
problem Efficient image transmission in noisy wireless channels.
method Joint source and channel coding using CNNs trained jointly.
result Deep JSCC outperforms traditional JPEG/2000 + channel codes at low SNR.
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 privacy-preserving method for transmitting data over a wiretap channel using generative networks.
problem Privacy protection in communication over a wiretap channel.
method Data-driven approach using variational autoencoder (VAE)-based joint source channel coding (JSCC).
result The approach provides high reconstruction quality at the receiver while confusing the eavesdropper about the latent sensitive attribute.
BottleNet++ compresses deep learning features for efficient mobile inference.
problem Balancing computation and communication in mobile devices with deep learning models.
method End-to-end architecture with encoder, non-trainable channel layer, and decoder.
result Achieves high compression ratio and bandwidth reduction with minimal accuracy loss.
Sparse coding, which represents a data point as a sparse reconstruction code with regard to a dictionary, has been a popular data representation method. Meanwhile, in database retrieval problems, learning the ranking scores from data points plays an important role. Up to now, these two problems have always been conside…
New scheme optimizes BMI through probabilistic and geometric shaping.
problem Optimizing bit-wise mutual information (BMI) for coded modulation.
method Joint optimization of BMI through probabilistic and geometric shaping.
result Joint optimization enables a continuum of constellation geometries and probability distributions.
This paper explores how random sampling and coding can speed up approximate matrix multiplication.
problem Efficiently computing large-scale matrix multiplications in distributed systems.
method Proposes two schemes: coding for recovery and random sampling for approximation.
result Investigates tradeoffs between recovery threshold and approximation error.
Improved multimodal variational models capture more complex joint distributions.
problem Limited expressiveness of multimodal variational models.
method Used normalizing flows to approximate and transform a simple parametric joint posterior into a more complex one.
result The model improves on state-of-the-art multimodal variational methods on various tasks.
Unsupervised method constructs knowledge graph from text and code.
problem Lack of structured knowledge in scientific literature and code.
method Word embedding, clustering, and dimensionality reduction techniques.
result Enhanced understanding of scientific literature and code.
Proposes baselines for joint NAS and HPO optimization.
problem Joint optimization of neural architecture and hyperparameters for multiple objectives.
method Extends existing methods to jointly optimize with multiple objectives.
result Serves as simple baselines for future multi-objective joint NAS + HPO research.
ProJIVE integrates multiple data types to explain joint and individual variation.
problem Integrating multiple types of data on the same subjects.
method Probabilistic EM algorithm for JIVE framework.
result ProJIVE learns biologically meaningful courses of variation and improves accuracy.
Study neural communication systems with bandwidth-limited channels.
problem Reliable message transmission despite noisy channels.
method Jointly model compression and error correction with neural networks; introduce prior for missing information; use auxiliary latent variables.
result Joint neural communication systems outperform separate models under expected information loss.
Model learns code representations from comments for data analysis tasks.
problem Lack of descriptive labels for analyzing large code corpora.
method Weakly supervised transformer architecture for joint code and comment representation.
result Model achieves 38% accuracy increase over expert-supplied heuristics.
Diffusion MRI (dMRI) provides the ability to reconstruct neuronal fibers in the brain, in vivo, by measuring water diffusion along angular gradient directions in q-space. High angular resolution diffusion imaging (HARDI) can produce better estimates of fiber orientation than the popularly used diffusion tens…
Embedding models for entities and relations are extremely useful for recovering missing facts in a knowledge base. Intuitively, a relation can be modeled by a matrix mapping entity vectors. However, relations reside on low dimension sub-manifolds in the parameter space of arbitrary matrices---for one reason, compositio…
Jointly tuning ensemble models improves performance and uncertainty calibration.
problem Improving both predictive performance and uncertainty calibration in deep ensembles.
method Investigated the impact of jointly tuning weight decay, temperature scaling, and early stopping.
result Jointly tuning ensemble models generally matches or improves performance, with significant variation across tasks.
Proposes a copula-driven framework for multimodal learning.
problem Aligning and fusing representations from multiple modalities with complex interactions.
method Copula model for joint distribution of modalities, Gaussian mixture for marginal distributions.
result Superior performance on public MIMIC datasets.
DeepBDC improves few-shot classification by measuring joint distributions of image features.
problem Few-shot classification with limited training data.
method DeepBDC method using deep learning and Brownian Distance Covariance.
result DeepBDC significantly outperforms existing methods on various benchmarks.
COBRA reduces modality gap in cross-modal tasks.
problem Joint embedding spaces fail to sufficiently reduce modality gap in multi-modal tasks.
method COBRA trains image and text modalities in a joint fashion using Contrastive Predictive Coding and Noise Contrastive Estimation.
result COBRA significantly reduces the modality gap and generates robust joint-embedding space.
Proposes a framework to improve VAE latent codes using mutual information.
problem Lack of explicit measure for VAE latent variable quality.
method Variational Mutual Information Maximization Framework.
result Improves relationships between latent codes and observations.
Generative AI decodes quantum codes without labeled data.
problem Efficient decoding of quantum error-correcting codes.
method Generative Transformers learn logical operators from unsupervised syndromes.
result Significantly better decoding accuracy than traditional methods.
Joint sparsity regularization in multi-task learning has attracted much attention in recent years. The traditional convex formulation employs the group Lasso relaxation to achieve joint sparsity across tasks. Although this approach leads to a simple convex formulation, it suffers from several issues due to the loosenes…
RD-Agent(Q) automates quantitative finance research and development.
problem Challenges in asset return prediction due to high dimensionality and volatility.
method Data-centric multi-agent framework for automated research and development of quantitative strategies.
result Up to 2X higher annualized returns with 70% fewer factors.
Proposes a hybrid deep learning network for better heart failure survival prediction.
problem Improving survival prediction in heart failure patients.
method Joint analysis of cardiac motion features and clinical risk factors using a hybrid deep learning network.
result Optimal integration of clinical risk factors into deep prediction networks.
Paper proposes a new method for joint feature selection and graph learning.
problem Previous methods suffer from neglecting joint formulation and lack of graph learning.
method Formulates multi-view feature selection with orthogonal decomposition, incorporates cross-space locality preservation, and uses a unified objective function for simultaneous learning.
result Demonstrates superior performance in multi-view feature selection and graph learning tasks.
A new method for joint noise removal and trend estimation from sparse signals.
problem Jointly removing noise and estimating trends from sparse signals.
method PENDANTSS combines SOOT/SPOQ penalties with BEADS algorithm in a Trust-Region block alternating variable metric forward-backward approach.
result Outperforms comparable methods in deconvolving analytical chemistry signals.
The paper forecasts joint electricity demand across 14 British regions using additive models.
problem Forecasting regional electricity demand with cross-regional dependencies.
method Modified Cholesky parametrisation for multivariate Gaussian model, gradient boosting for model selection.
result The proposed model outperforms non-Gaussian copula-based models in forecasting.
In this work, we formulate the fixed-length distribution matching as a Bayesian inference problem. Our proposed solution is inspired from the compressed sensing paradigm and the sparse superposition (SS) codes. First, we introduce sparsity in the binary source via position modulation (PM). We then present a simple and …
A new method for energy-efficient file delivery in small cell networks.
problem Efficient resource management in femto-caching with time-variant statistical properties.
method Formulates a resource allocation problem as a stochastic knapsack problem and a multi-armed bandit problem, developing solutions for each.
result The proposed method maximizes the accumulated utility over the horizon, especially suitable for networks with time-variant statistical properties.
Directed latent variable models that formulate the joint distribution as p(x,z)=p(z)p(x∣z) have the advantage of fast and exact sampling. However, these models have the weakness of needing to specify p(z), often with a simple fixed prior that limits the expressiveness of the model. Undirected latent variabl…
NeuralFLoC unifies registration and clustering of functional data, overcoming phase variation challenges.
problem Challenges in clustering functional data due to phase variation and temporal misalignment.
method NeuralFLoC uses Neural ODE-driven diffeomorphic flows and spectral clustering for joint registration and clustering.
result NeuralFLoC effectively disentangles phase and amplitude variation, achieving state-of-the-art performance.
A new multi-label CPC method improves mutual information estimation and representation learning.
problem Underestimation of mutual information in contrastive predictive coding.
method Introducing a multi-label classification problem to overcome the logm bound in mutual information estimation. result The new method exceeds the logm bound and leads to better mutual information estimation and improved unsupervised representation learning. Improves EM algorithm for better local optima in mixture models.
problem EM algorithm's sensitivity to initialization and bad local optima.
method Big Learning principle applied to upgrade EM algorithm.
result BigLearn-EM delivers optimal solution with high probability.
APQ jointly optimizes neural architecture, pruning, and quantization for efficient inference.
problem Efficient deep learning inference on resource-constrained hardware.
method Joint optimization of neural architecture, pruning, and quantization policy using a quantization-aware accuracy predictor.
result Joint optimization leads to 2.3% higher ImageNet accuracy with reduced latency and energy consumption.
New method models MTPP without predefined intensity functions.
problem Parameterizing conditional joint PDF for MTPP.
method IFIB framework, modeling p∗(m,t) directly. result Superior experimental results on real and synthetic data.
Dictionary learning algorithms have been successfully used for both reconstructive and discriminative tasks, where an input signal is represented with a sparse linear combination of dictionary atoms. While these methods are mostly developed for single-modality scenarios, recent studies have demonstrated the advantages …
Paper studies distributed learning with limited communication bits, achieving optimal error exponents.
problem Distributed hypothesis testing with constant communication bits.
method Geometric approach in distribution spaces, encoding empirical distributions to transmission bits.
result Optimal achievable error exponents and coding schemes for various communication constraints.
Symile learns joint representations across multiple modalities, outperforming pairwise CLIP.
problem Pairwise contrastive learning fails to capture joint information between multiple modalities.
method Symile uses a flexible, architecture-agnostic objective to learn modality-specific representations by deriving a lower bound on total correlation.
result Symile outperforms pairwise CLIP on cross-modal classification and retrieval across various datasets.
Graphical models help infer domain adaptation across unknown distributions.
problem Unknown changes in joint distribution across domains.
method Use graphical models to encode and infer changes in data distribution.
result Automated domain adaptation framework improves posterior inference of target variable.
A new method compresses point clouds efficiently, outperforming existing techniques.
problem Efficiently compressing large point cloud datasets for VR applications.
method Learned convolutional transforms and uniform quantization for joint rate and distortion optimization.
result Significant rate-distortion improvement (51.5% BDBR savings) on Microsoft Voxelized Upper Bodies dataset.
LMConv improves autoregressive models for image generation and completion.
problem Limited generation order in autoregressive models restricts their applicability.
method Introduces LMConv, a modified 2D convolution that allows arbitrary masks to be applied to weights.
result LMConv achieves improved performance on image density estimation and coherent completions.
Unsupervised methods have proven effective for discriminative tasks in a single-modality scenario. In this paper, we present a multimodal framework for learning sparse representations that can capture semantic correlation between modalities. The framework can model relationships at a higher level by forcing the shared …
A novel method learns word embeddings and topics using Wasserstein distance.
problem Learning word embeddings and topics from text data.
method Distilled Wasserstein learning framework for joint word embedding and topic modeling.
result Superior performance on disease network construction, mortality prediction, and procedure recommendation.
New framework improves LLM performance by avoiding forgetting during sequential training stages.
problem Forgetting during sequential training stages of LLMs.
method Proposes a joint post-training framework with theoretical convergence guarantees.
result Empirically outperforms sequential post-training framework by up to 23%.
Paper introduces FJD metric for cGAN benchmarking.
problem Quantitative evaluation of cGANs using multiple metrics.
method Frechet Joint Distance (FJD) metric.
result FJD provides a single metric for cGAN benchmarking and model selection.
CodedReduce combines tree topology and gradient coding for efficient and resilient gradient aggregation.
problem Efficient and robust gradient aggregation in distributed learning.
method CodedReduce combines tree topology and gradient coding to overcome bandwidth bottlenecks and straggler delays.
result CodedReduce achieves up to 27.2x speedup over benchmarks GC and RAR.