Paper studies fully implicit online learning algorithms for improved numerical stability.
problem Improving numerical stability and solution structure in online learning.
method Develops fully implicit online learning (FIOL) algorithms without linearizing loss or regularizer.
result FIOL achieves optimal regret bounds for convex and strongly convex settings.
In this paper, we make a generalization of Routh's reduction method for Lagrangian systems with symmetry to the case where not any regularity condition is imposed on the Lagrangian. First, we show how implicit Lagrange-Routh equations can be obtained from the Hamilton-Pontryagin principle, by making use of an anholonom…
Gradient descent in deep matrix factorization favors low-rank solutions, improving recovery accuracy.
problem Understanding the generalization in deep learning models.
method Study of gradient descent over deep linear neural networks for matrix completion and sensing.
result Adding depth enhances an implicit tendency towards low-rank solutions, leading to more accurate recovery.
Paper proposes DAG-DB for learning discrete DAGs via backpropagation.
problem Learning Directed Acyclic Graphs (DAGs) from data.
method DAG-DB uses Discrete Backpropagation with I-MLE and Straight-Through Estimation.
result DAG-DB learns DAGs effectively using probabilistic sampling and backpropagation.
New method separates objects from images using deep neural networks trained to inpaint.
problem Fully self-supervised instance separation of occluded objects in images.
method Maximizes independence of two image regions given a fully self-supervised inpainting network.
result Method achieves similar segmentation performance to fully supervised methods on microscopy image datasets.
Gradient descent biases towards stable rank networks for nearly-orthogonal data.
problem Understanding implicit bias in non-smooth neural networks trained by gradient descent.
method Analysis of two-layer ReLU and leaky ReLU networks trained by gradient descent on nearly-orthogonal data.
result Gradient descent biases towards networks with stable rank and uniform margin for nearly-orthogonal data.
A new Gaussian process regression method infers implicit manifold structure from data.
problem Scaling Gaussian process regression to high-dimensional data.
method Proposes a fully differentiable Gaussian process regression technique that infers implicit manifold structure from data.
result Improves predictive performance and calibration of standard Gaussian process regression in high-dimensional settings.
SIP corrects model bias in Bayesian ML.
problem Model selection biases predictions in Bayesian ML.
method Sparse Implicit Processes (SIP) for flexible, trainable predictions.
result SIP provides better predictive distributions than initial models.
XLVINs improve data efficiency in implicit planning by leveraging latent space.
problem Improving data efficiency in implicit planning algorithms.
method XLVINs use a high-dimensional latent space to perform planning computations, breaking the algorithmic bottleneck.
result XLVINs significantly improve data efficiency across various settings compared to value iteration-based implicit planners and model-free baselines.
Efficiently integrates stiff ODEs with vectorized methods.
problem Stiff systems and sparse training data in ODEs.
method Implicit, vectorized time integration with adjoint method.
result Achieves speed ups of greater than 100x on modern GPUs.
This study investigates how gradient-based methods bias neural networks trained on high-dimensional data.
problem The implicit biases of gradient-based optimization algorithms in neural networks trained on high-dimensional data.
method Investigation of gradient flow and gradient descent in two-layer fully-connected neural networks with leaky ReLU activations.
result Gradient flow and gradient descent lead to neural networks with low-rank solutions and linear decision boundaries.
We show that gradient descent on full-width linear convolutional networks of depth L converges to a linear predictor related to the ℓ2/L bridge penalty in the frequency domain. This is in contrast to linearly fully connected networks, where gradient descent converges to the hard margin linear support vector m…
Proposes a deep learning model for timely and accurate recommendations.
problem Inability to provide timely recommendations and ranking issues with implicit feedback.
method Unified cross-network solution using listwise ranking for implicit data.
result Superior performance in accuracy, novelty, and diversity compared to baselines.
In recent years, deep neural networks have yielded state-of-the-art performance on several tasks. Although some recent works have focused on combining deep learning with recommendation, we highlight three issues of existing models. First, these models cannot work on both explicit and implicit feedback, since the networ…
The paper explores how the depth of neural networks affects their ability to represent data accurately.
problem Understanding the implicit bias and rank of neural networks with large depth.
method Analyzing the convergence of representation cost to a notion of rank as network depth increases, and investigating conditions for recovering the true rank of data.
result There is a range of network depths where the true rank of data is recovered, and this affects the topology of class boundaries.
Improved method for unbiased causal discovery in presence of unobserved confounding.
problem Unbiased data synthesis for causal discovery algorithms in the presence of unobserved confounding.
method Explicit block-hierarchical ancestral sampling to address limitations of implicit parameterization.
result Our approach fully covers the space of causal models, including those generated by implicit parameterization.
A new framework for offline RL improves policy flexibility and regularity.
problem Lack of environmental interactions in offline RL leads to poor policy performance.
method Proposes a behavior-regularized implicit policy framework with modified policy-matching methods.
result The framework improves policy effectiveness and robustness beyond static datasets.
This work studies the implicit bias of mini-batch SGD in classification.
problem Understanding the implicit bias of mini-batch SGD in multi-class classification.
method Characterizes how batch size, momentum, and variance reduction affect convergence and max-margin behavior under different norms.
result Momentum enables small-batch convergence to an approximate max-margin solution, while variance reduction recovers the exact full-batch bias.
New tensor formulation reveals gradient flow's bias in linear neural networks.
problem Understanding implicit bias in linear neural network training.
method Tensor formulation of neural networks, including fully-connected, diagonal, and convolutional networks.
result Gradient flow on linear tensor networks converges to solutions of specific optimization problems.
RL struggles with generalization due to implicit partial observability.
problem Generalization in RL is difficult due to implicit partial observability.
method Re-cast RL problem as solving epistemic POMDPs and propose ensemble-based techniques.
result Simple ensemble-based technique achieves significant generalization gains.
We study alignment in linear neural networks and its relation to gradient descent.
problem Understanding alignment in linear neural networks and its impact on training.
method Defined alignment for fully connected networks, analyzed alignment under gradient descent, and compared gradient descent to projected gradient descent for layer-constrained networks.
result Gradient descent can converge linearly to a global minimum when alignment is invariant, and alignment is impossible with large datasets in layer-constrained networks.
Atrial Fibrillation (AF) is a common electro-physiological cardiac disorder that causes changes in the anatomy of the atria. A better characterization of these changes is desirable for the definition of clinical biomarkers, furthermore, thus there is a need for its fully automatic segmentation from clinical images. In …
In this paper we propose and analyze a method based on the Riccati transformation for solving the evolutionary Hamilton-Jacobi-Bellman equation arising from the stochastic dynamic optimal allocation problem. We show how the fully nonlinear Hamilton-Jacobi-Bellman equation can be transformed into a quasi-linear paraboli…
It is known that the implied volatility skew of FX options demonstrates a stochastic behavior which is called stochastic skew. In this paper we create stochastic skew by assuming the spot/instantaneous variance correlation to be stochastic. Accordingly, we consider a class of SLV models with stochastic correlation wher…
Pricing and hedging exotic options using local stochastic volatility models drew a serious attention within the last decade, and nowadays became almost a standard approach to this problem. In this paper we show how this framework could be extended by adding to the model stochastic interest rates and correlated jumps in…
New communication topologies improve deep reinforcement learning performance.
problem Improving performance of learning agents in distributed reinforcement learning.
method Examined four graph families for communication topologies and found Erdos-Renyi random graphs to outperform fully connected topologies.
result Erdos-Renyi random graphs can improve performance of distributed learning agents.
Neural circuits integrate continuous dynamics efficiently.
problem Efficiently integrating continuous neural dynamics for simulation and learning.
method Compact neural circuits for Runge-Kutta and Adams-Bashforth-Moulton methods.
result Equivalence of neural and numerical integration for polynomial systems.
The paper solves a dynamic portfolio optimization problem using Riccati transformation.
problem Dynamic stochastic portfolio optimization involving expected and intertemporal utilities.
method Solving a fully nonlinear HJB equation through Riccati transformation into a quasi-linear parabolic equation.
result The numerical method based on semi-implicit scheme converges at second order.
This paper shows how to train only the implicit layer of overparameterized implicit neural networks.
problem Understanding how the implicit layer contributes to the training of overparameterized implicit neural networks.
method Restricting training to only the implicit layer and analyzing the generalization error for ReLU-activated networks.
result Global convergence is guaranteed even if only the implicit layer is trained, and gradient flow with proper random initialization can achieve small generalization errors.
Paper studies the theoretical equivalence between implicit and explicit neural networks in high dimensions.
problem Lack of theoretical analysis of implicit and explicit neural networks.
method Examined high-dimensional implicit neural networks and established their equivalence to explicit networks.
result Equivalence between implicit and explicit neural networks in high dimensions.
Gradient matching method estimates implicit regularization in complex deep learning systems.
problem Estimating implicit regularization in modern deep learning systems with complex modifications.
method Gradient matching methods to empirically estimate implicit regularization.
result Empirical estimation of implicit regularization in arbitrary networks, including dropout.
Analysis of gradient descent on wide neural networks reveals strong generalization.
problem Understanding why wide neural networks trained with logistic loss perform well.
method Characterization of gradient flow limits and comparison to max-margin classifier.
result Margin is independent of ambient dimension, leading to strong generalization.
Continuous semi-implicit models enable faster training and better performance in generative modeling.
problem Slow convergence in hierarchical semi-implicit models during training.
method CoSIM, a continuous semi-implicit model that incorporates a continuous transition kernel for efficient training.
result CoSIM achieves superior performance on image generation tasks compared to existing methods.
New algorithm improves kernel-based deep net performance.
problem Understanding deep learning and its mysteries.
method Exact computation of Convolutional NTK (CNTK) for infinite-width convolutional nets.
result CNTK results in 10% higher performance on CIFAR-10 than previous methods. Gradient descent converges to a global minimum in nonlinear ReLU implicit networks with linear width.
problem Understanding convergence of gradient methods in nonlinear, infinitely deep ReLU networks.
method Introduced a scaling constant to ensure well-posedness of the equilibrium equation, proving convergence to a global minimum for linear width networks.
result Gradient descent converges to a global minimum at a linear rate for nonlinear ReLU implicit networks with linear width.
DSIVI improves variational autoencoders by optimizing a proper lower bound on ELBO.
problem Improving variational autoencoders with implicit priors.
method Introducing DSIVI, a method that optimizes a proper lower bound on ELBO for models with semi-implicit priors and posteriors.
result DSIVI improves the performance of VampPrior, a state-of-the-art prior for variational autoencoders.
Study finds implicit government guarantee improves municipal investment bond ratings.
problem Questioning the objectivity of municipal investment bond ratings due to implicit government guarantee.
method Text mining of policy documents and PMC index model for implicit guarantee strength calculation.
result Implicit government guarantee boosts municipal investment bond ratings, especially in less developed regions.
Study shows SGD's generalization is not explained by implicit bias.
problem Explaining the generalization ability of overparameterized learning algorithms.
method Revisited Stochastic Convex Optimization with SGD, demonstrating limitations of implicit bias.
result No distribution-independent or distribution-dependent implicit regularizer can explain SGD's generalization.
This paper measures the intensity of implicit government guarantees using PMC index model.
problem Excessive local government debt due to implicit government guarantees.
method Text mining of policy documents related to municipal investment bonds, PMC index model.
result Recent policies have reduced the intensity of implicit government guarantees.
Networks play a central role in modern data analysis, enabling us to reason about systems by studying the relationships between their parts. Most often in network analysis, the edges are given. However, in many systems it is difficult or impossible to measure the network directly. Examples of latent networks include ec…
The paper explains implicit regularization in hierarchical tensor factorization and deep CNNs.
problem Understanding implicit regularization in complex neural network architectures.
method Theoretical analysis using dynamical systems to overcome challenges in hierarchy.
result Established implicit regularization towards low hierarchical tensor rank, equivalent to locality in CNNs.
In this paper, we describe the "implicit autoencoder" (IAE), a generative autoencoder in which both the generative path and the recognition path are parametrized by implicit distributions. We use two generative adversarial networks to define the reconstruction and the regularization cost functions of the implicit autoe…
Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another …
Deep tensor factorization benefits from implicit regularization with polynomial growth.
problem Tensor factorization's implicit regularization effect in deep networks is not well understood.
method Investigated the implicit regularization in deep tensor factorization, showing polynomial growth.
result Implicit regularization in deep tensor factorization grows polynomially with depth, improving estimation accuracy and convergence.
A new optimisation framework for neural networks without hyperparameters.
problem Lack of explicit architectural information in optimisation frameworks.
method Extends mirror descent to account for neural architecture, transforming a Bregman divergence.
result Automatic gradient descent: a first-order optimiser without hyperparameters.
Gradient descent on ReLU networks with square loss implicitly favors balanced weights.
problem Understanding implicit regularization in nonlinear neural networks with regression losses.
method Analyzing gradient descent dynamics on ReLU networks with square loss.
result It is impossible to characterize the implicit regularization of ReLU networks with square loss by any explicit function of model parameters.
New insights into how deep models generalize, focusing on matrix factorization.
problem Understanding how deep models generalize and why they work well.
method Using Morse functions and dynamical systems to study implicit regularization.
result Solved a conjecture on implicit regularization in matrix factorization.
Deep equilibrium models converge globally without explicit computation.
problem Global convergence of deep learning models with implicit layers.
method Analysis of gradient dynamics and proof of convergence rate.
result Deep equilibrium models converge to global optimum at a linear rate.