Proposes a new deep ordinal classification model enforcing label uni-modality.
problem Deep ordinal classification with label consistency issues.
method Non-parametric uni-modality constraints via inequality constraints.
result Improves scalability and performance in ordinal classification tasks.
A new memory-based fusion layer improves multi-modal deep learning performance.
problem Improving performance of multi-modal deep learning by addressing long-term dependencies.
method Introducing a Memory based Attentive Fusion (MBAF) layer that incorporates both current and long-term dependencies.
result The MBAF layer enhances fusion and improves performance across different modalities and networks.
Boltzmann machines are undirected graphical models with two-state stochastic variables, in which the logarithms of the clique potentials are quadratic functions of the node states. They have been widely studied in the neural computing literature, although their practical applicability has been limited by the difficulty…
Prediction of future states of the environment and interacting agents is a key competence required for autonomous agents to operate successfully in the real world. Prior work for structured sequence prediction based on latent variable models imposes a uni-modal standard Gaussian prior on the latent variables. This indu…
The paper improves SMC algorithm for multi-modal distributions by proving variance bounds.
problem Problems with SMC on multi-modal distributions, especially in terms of mixing time.
method Proves variance bounds for SMC on multi-modal distributions using soft decomposition.
result Bounds on SMC variance depend on local rather than global mixing times.
Develops multi-modal neural network models for improved prediction and uncertainty quantification.
problem Improving prediction accuracy and uncertainty quantification for multi-modal data.
method Multi-modal Bayesian neural network models with conjugate last-layer estimation using SVI.
result Improved prediction accuracy and uncertainty quantification compared to uni-modal models.
ROME improves density estimation for multi-modal, non-normal data.
problem Robust multi-modal density estimation in non-normal, highly correlated distributions.
method ROME uses clustering to segment multi-modal data into uni-modal clusters, then combines KDE estimates for each cluster.
result ROME outperforms state-of-the-art methods and is more robust to various distributions.
A new method simplifies sampling from complex distributions without using diffusions.
problem Sampling from complex, high-dimensional distributions efficiently.
method Reduces sampling to solving a sequence of 'nice' sampling problems using SLC distributions.
result Shows how to traverse backwards paths using high-accuracy routines for SLC distributions.
Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition. For certain concepts, vis…
Proposes a parametric modal regression method using the implicit function theorem.
problem Finding conditional modes for multi-modal conditional distributions.
method Uses the implicit function theorem to develop an objective function for learning a joint function over inputs and targets.
result Empirically demonstrates scalability and effectiveness in learning multi-valued functions and high-dimensional inputs.
EMDE efficiently estimates manifold densities for diverse recommendation systems.
problem Efficiently estimating manifold densities for multi-modal recommendation systems.
method EMDE (Efficient Manifold Density Estimator) framework for arbitrary vector representations.
result Established new state-of-the-art results in top-k and session-based recommendation settings.
In many situations, we need to build and deploy separate models in related environments with different data qualities. For example, an environment with strong observation equipments (e.g., intensive care units) often provides high-quality multi-modal data, which are acquired from multiple sensory devices and have rich-…
This paper investigates the problem of recovering missing samples using methods based on sparse representation adapted especially for image signals. Instead of l2-norm or Mean Square Error (MSE), a new perceptual quality measure is used as the similarity criterion between the original and the reconstructed images. T…
BOinG optimizes HPO problems by focusing on promising local regions.
problem Expensive black-box optimization problems, especially hyperparameter optimization.
method Two-stage approach: global surrogate model followed by local model.
result BOinG exploits the structure of typical HPO problems and performs well on mid-sized problems.
A key task in Bayesian statistics is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). However, without any assumptions, sampling (even approximately) can be #P-hard, and few works have provided "beyond worst-case" guarantees for such settings. For log-c…
The study optimizes sampling in complex systems with probabilistic response distributions.
problem Calibrating and optimizing complex systems with probabilistic response distributions.
method Non-parametric Bayesian approach to modeling spatial fields of probability distributions, introducing adaptive sampling strategies.
result Adaptive sampling strategies improve system evaluations by guiding focus towards key features.
Langevin Dynamics fails to sample from mixture distributions efficiently.
problem Analyzing Langevin Dynamics for sampling from mixture distributions.
method Theoretical analysis of Langevin Dynamics and proposing Chained-Langevin Dynamics.
result Langevin Dynamics fails to sample from mixture distributions efficiently.
GROOVE learns representations for weakly paired multimodal data.
problem Learning representations for high-content perturbation data with weakly paired samples.
method GroupCLIP contrastive loss integrated with an autoencoder framework.
result GROOVE performs on par with or outperforms existing approaches for cross-modal tasks.
The paper proposes a new method to forecast winning prices in real-time bidding.
problem Accurately forecasting winning prices in real-time bidding with limited data.
method The paper introduces a heteroscedastic fully parametric censored regression approach and a mixture density censored network.
result The proposed method significantly improves winning price forecasting compared to existing methods.
A key task in Bayesian machine learning is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). One prevalent example of this is sampling posteriors in parametric distributions, such as latent-variable generative models. However sampling (even very approxim…
Paper uses CNN to predict process parameters from molten pool data in WLAM.
problem Achieving high quality in WLAM through real-time process control.
method Proposes a multi-modality CNN architecture to predict process parameters from molten pool sensor data.
result Improved prediction performance of multi-modal CNN compared to uni-modal approach.
This study examines non-retail trading on Polymarket, revealing unique behavior patterns and structural limitations.
problem Lack of address-level quote-lifecycle data in Polymarket prediction markets.
method Empirical analysis of 13 million order-filled events using DBSCAN clustering on a six-feature fill-side vector.
result Non-retail behavior is uni-modal, contradicting previous archetypal hypotheses.