Generative model ensures valid discrete data outputs.
problem Challenges in generative modeling of discrete data like arithmetic expressions and molecular structures.
method Grammar Variational Autoencoder (GVAE) that encodes and decodes to/from parse trees, ensuring valid outputs.
result Generates more coherent latent space with valid discrete outputs.
CADD improves generative quality by augmenting discrete diffusion with continuous latent space.
problem Loss of semantic information between denoising steps in discrete diffusion models.
method Introduces a framework that augments discrete state space with a continuous latent space, allowing for graded, informative masked tokens.
result CADD improves generative quality across text generation, image synthesis, and code modeling.
Proposes hybrid reinforcement learning for both discrete and continuous control problems.
problem Real-world control problems involving both discrete and continuous decision variables.
method Solves hybrid problems by optimizing for discrete and continuous actions simultaneously.
result Efficiently solves hybrid reinforcement learning problems and improves upon expert heuristics.
Framework estimates multiple plausible solutions with uncertainty measures.
problem Machine learning models need to propose multiple plausible solutions with meaningful uncertainty.
method Discrete latent variables model one-to-many mappings, allowing effective conditional probability estimation.
result Framework outperforms state-of-the-art in uncertainty estimation and is practical.
A new method quantizes output space for multi-target regression.
problem Predicting multiple continuous targets using shared predictors.
method MRQ method that quantizes output space to model dependencies and scale.
result MRQ achieves high scalability and competitive accuracy.
A new framework for structured prediction on non-vectorial spaces.
problem Structured prediction on non-vectorial output spaces.
method Defining a suitable geometry for implicit loss functions.
result Efficient algorithmic framework with sharp statistical analysis.
Duel-Evolve uses LLM self-preferences for test-time optimization of discrete outputs.
problem Optimizing LLM outputs at test time with limited or unreliable scalar rewards.
method Duel-Evolve uses pairwise comparisons from the LLM to guide optimization, aggregating them via a Bayesian Bradley-Terry model.
result Achieves significant improvement over existing methods in accuracy.
State-space systems generate probabilistic dependencies between inputs and outputs.
problem Understanding probabilistic dependencies in state-space systems.
method Introducing a probabilistic framework and proving sufficient conditions for output existence and uniqueness.
result State-space systems can generate probabilistic dependencies, even without functional relations.
We find a normal form for two-input flat discrete-time systems.
problem No comparable normal form exists for flat continuous-time systems.
method State- and input transformations to achieve a triangular structure.
result A systematic parameterization of system variables by the flat output and its shifts.
Decomposes flat nonlinear discrete-time systems into simpler components.
problem Flatness of nonlinear discrete-time systems.
method Coordinate transformations and feedback, using flow-box and Frobenius theorems.
result Flatness of a discrete-time system can be checked algorithmically.
RI-DeepONet learns neural operators from arbitrary sensor data.
problem Discretization of input functions limits practical applications of DeepONet.
method Introduces RI-DeepONet and two dictionary learning algorithms for INRs.
result RINO handles arbitrary sensor data robustly and applies to various problems.
The paper proves that linearization along trajectories preserves flatness in discrete-time systems.
problem The relation between nonlinear and linear time-varying systems.
method Linearization along trajectories of a flat discrete-time system.
result The linearized system is flat, and a flat output can be derived.
Paper tackles natural language generation using GANs, achieving state-of-the-art results.
problem Discrepancy in progress between image and natural language generation using GANs.
method Introduces a simple baseline for generating natural language from noise without gradient estimators.
result Achieves state-of-the-art results on a Chinese poem generation dataset.
Graph Kalman filters adapt classical filters to graph data.
problem Adapting classical Kalman filters to graph data.
method Generalizes Kalman filters to attributed graphs, learning state-transition and readout functions end-to-end.
result Adapted Kalman filters can predict graph outputs.
Earth observation embeddings can convert discrete biome maps into continuous representations that better capture ecological variation.
problem Biome maps impose categorical boundaries that compress continuous variation in biotic communities.
method Fit a linear classifier on Earth observation embeddings to predict biome labels.
result Continuous biome representation outperforms discrete biome labels for predicting species occurrence.
Improved text generation with constraints using discrete auto-regressive biasing.
problem Balancing fluency and constraint satisfaction in LLM outputs.
method Discrete Auto-regressive Biasing, leveraging gradients in discrete text space.
result Significantly improved constraint satisfaction with comparable fluency.
This work develops discrete Gaussian models for vector-valued data on triangular meshes.
problem Discrete representation of continuous vector-valued environmental data.
method Develops discrete intrinsic Gaussian processes for vector-valued data on triangular meshes using discrete differential operators.
result Models can capture harmonic flows, incorporate boundary conditions, and model non-stationary data.
Develops neural network approximations for infinite-dimensional input-output maps.
problem Approximating input-output maps between infinite-dimensional spaces.
method Combines neural networks and model reduction techniques.
result Proves convergence of the proposed approximation methodology.
Paper corrects Max-Margin loss for multi-label tasks.
problem Max-Margin loss inconsistency in multi-label classification.
method Introduced Restricted-Max-Margin loss.
result Consistent loss for multi-label tasks under milder conditions.
The paper tackles exact linearization and control of flat discrete-time systems.
problem Exact linearization and control of flat nonlinear discrete-time systems.
method Investigates conditions for choosing new inputs and feedbacks that may depend on forward-shifts of the new input.
result Easily verifiable conditions for choosing a feasible input and a new input that minimizes forward-shifts of the flat output.
Random feature model approximates PDE solutions efficiently.
problem Approximating solutions to PDEs with high-dimensional inputs and outputs.
method Random feature model applied to infinite-dimensional operators.
result Efficient and accurate approximation of PDE solutions.
The paper tackles fast rates in structured prediction problems.
problem Structured prediction problems with discrete outputs.
method Introducing continuous surrogate problems and leveraging their convergence rates for discrete problems.
result Super fast rates, including exponential rates, for excess risk in structured prediction problems.
DNAF accelerates DQL for efficient resource allocation in network slicing.
problem Efficient resource allocation in network slicing with varying demands.
method Introduced discrete normalized advantage functions (DNAF) into DQL, using a k-nearest neighbor algorithm for discrete action space.
result DNAF-based DQL converges faster through simulations.
Physics-informed neural operator learns from coarse to fine discretized data.
problem Lack of high-fidelity training data and uneven grid resolution.
method Physics-informed multi-resolution neural operator framework.
result Learn from arbitrarily discretized input functions using latent embedding and finite difference solver.
We develop a method for quantile-based sensitivity analysis in models with discontinuities.
problem Uncertainty in interpreting discontinuous models using traditional derivatives.
method Quantile-based derivatives for discontinuous models with discrete inputs.
result Derivatives of quantile-based outputs are well-defined and provide meaningful insights.
Unsupervised framework captures acquisition variability in structural connectomes.
problem Acquisition differences across sites, scanners, and protocols complicate structural connectome analysis.
method An unsupervised framework using architectural annealing to balance discrete and continuous latent variables.
result Architectural annealing produces stronger site learning than baseline models.
TPGR uses a tree structure to improve efficiency and effectiveness in large-scale interactive recommendation.
problem Efficiency and effectiveness in large-scale interactive recommendation systems with thousands of items.
method Tree-structured Policy Gradient (TPGR) framework for handling large discrete action spaces.
result Superior recommendation performance and significant efficiency improvement over state-of-the-art methods.
Remasking improves the quality of discrete diffusion models for natural language and image generation.
problem Limited iterative refinement in masked discrete diffusion models.
method Introducing ReMDM sampler that allows remasking during inference.
result Remasking enables better quality outputs with increased sampling steps.
This work bounds the generalization error of private algorithms for discrete data.
problem Bounding the generalization error of private algorithms for discrete data.
method Information-theoretic approach using relative entropy and the method of types.
result Explicit upper bounds on the generalization error of stable private algorithms for discrete data.
Neural Jump ODEs extend to infinite-dimensional function spaces for optimal prediction.
problem Handling continuous-time stochastic processes in infinite-dimensional function spaces.
method Developing a new approximation strategy for infinite-dimensional function-valued processes.
result Proved convergence of the NJ-ODE to the optimal prediction process.
GANs use Gumbel-softmax for generating sequences of discrete elements.
problem GANs struggle with discrete sequences due to non-differentiability of multinomial distributions.
method Used Gumbel-softmax distribution as a continuous approximation to a multinomial distribution for discrete elements.
result GANS with Gumbel-softmax outperform traditional GANs in generating sequences of discrete elements.
Improved training for VQ-VAE models with robust codebook learning.
problem Challenges in training discrete latent variable models, especially VQ-VAEs.
method Increased learning rate and periodic re-initialization of codebook for robust training.
result More robust training and increased usage of latent codewords, even for large codebooks.
New methods improve Deep Reinforcement Learning in parameterized action spaces.
problem Efficient training in tasks with parameterized action spaces.
method Compact architecture and new training methods based on TRPO and SVG.
result New methods outperform state-of-the-art Parameterized Action DDPG.
VAIOM models financial returns using continuous input and categorical output.
problem Modeling continuous, noisy, and heterogeneous financial data.
method VAIOM is a decoder-only Transformer that separates input representation from output likelihood.
result VAIOM models outperform fixed single-bar LightGBM baseline in both Test halves.
BestChanID identifies the channel with maximal capacity using training sequences.
problem Identifying the channel with maximal capacity among several discrete memoryless channels.
method Formulated as a multi-armed bandit problem, proposed a capacity estimator, and developed gap-elimination algorithms.
result Guaranteed to output the DMC with the largest capacity with a desired confidence.
We introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such problems cannot be trivially addressed by existent approaches such as sequence-to-sequence and Neural Turing Machines, because th…
Quantum algorithm finds extremal values without direct function access.
problem Finding extremal values of hidden functions without direct access.
method Parametric quantum circuit trained with a trainable quantum feature map.
result Algorithm successfully finds extremal values even with sparse training data.
Piano Genie lets non-musicians improvise on a piano.
problem Improvising on the piano for non-musicians.
method Trained recurrent neural network autoencoders with discrete bottlenecks to learn mappings between user inputs and piano pieces.
result Piano Genie allows users to improvise on the piano with musically meaningful constraints.
Neural networks learn discrete tasks on continuous data via emergent geometry.
problem Understanding how neural networks perform discrete computations on continuous data.
method Analysis of Riemannian pullback metric across neural network layers.
result Neural networks learn to discretize continuous inputs and perform logical operations on these discretized variables.
We address the task of simultaneous feature fusion and modeling of discrete ordinal outputs. We propose a novel Gaussian process(GP) auto-encoder modeling approach. In particular, we introduce GP encoders to project multiple observed features onto a latent space, while GP decoders are responsible for reconstructing the…
Study shows consistency of shallow GCNNs on sampled point clouds under manifold assumption.
problem Consistency of shallow GCNNs on sampled point clouds under manifold assumption.
method Functional analysis perspective, weakly compact product of unit balls, Sobolev regularity, frequency cutoff.
result Proves Γ-convergence of regularized empirical risk minimization functionals and convergence of their global minimizers. Study error bounds in evaluating distributional computational graphs.
problem Error analysis in evaluating graphs with inputs as probability distributions.
method Establish non-asymptotic error bounds using Wasserstein-1 distance.
result Non-asymptotic error bounds for discretization errors in distributional computational graphs.
New framework optimizes neural networks using ODEs instead of discrete methods.
problem Optimizing neural networks using discrete methods.
method Port-Hamiltonian approach to learning neural networks.
result Ensures convergence to minimum of objective function.
Discrete Gaussian noise preserves privacy and accuracy in differential privacy.
problem Finite computers cannot represent continuous Gaussian noise, leading to privacy breaches and loss of interpretability.
method Introduced and analyzed discrete Gaussian noise, providing privacy and accuracy guarantees similar to continuous Gaussian noise.
result Discrete Gaussian noise offers the same privacy and accuracy as continuous Gaussian noise, with efficient sampling algorithms.
Proposes a new GAN framework for discrete data generation.
problem Difficulty in passing gradients from discriminator to generator for discrete data.
method Adversarial approach with iterative generator definition based on discriminator.
result Improves discrete data generation quality and diversity compared to GANs and ML.
A new mutual information lower bound for multimodal regression active learning.
problem Lack of effective acquisition functions for multimodal regression active learning.
method Introduces a Two-Index framework for separating epistemic and aleatoric sources of uncertainty, deriving MI-LB as a closed-form approximation.
result MI-LB consistently outperforms baselines on multimodal regression tasks.
Many machine learning tasks can be expressed as the transformation---or \emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and text-to-speech to name but a few. One of the key challenges in sequence transduction is learning to …
Differential privacy is a framework for privately releasing summaries of a database. Previous work has focused mainly on methods for which the output is a finite dimensional vector, or an element of some discrete set. We develop methods for releasing functions while preserving differential privacy. Specifically, we sho…