Study learns cost functions from user behavior using Wasserstein optimization.
problem Learning a user's true cost function from observed behavior.
method Unified KL framework and two-step Wasserstein inverse optimal control.
result Significant performance gains over existing methods in recommender systems and social networks.
Inverse optimal control, also known as inverse reinforcement learning, is the problem of recovering an unknown reward function in a Markov decision process from expert demonstrations of the optimal policy. We introduce a probabilistic inverse optimal control algorithm that scales gracefully with task dimensionality, an…
VICE uses events to define rewards without expert demonstrations.
problem Designing effective reward functions for reinforcement learning.
method VICE generalizes inverse reinforcement learning to use event probabilities.
result VICE achieves high performance on complex tasks with high-dimensional observations.
New method disentangles perceptual uncertainty and behavioral costs in partially observable systems.
problem Tackles inverse optimal control for non-linear partially observable systems.
method Probabilistic approach using maximum causal entropy formulations and local linearization.
result Disentangles perceptual factors and behavioral costs in sequential decision-making.
New method reduces variance in Bayesian inverse problems.
problem High variance in Monte Carlo estimates for inverse problems.
method Conditional neural control variates based on Stein's identity.
result Substantial variance reduction across different inverse problems.
New method for PKM inverse dynamics second derivatives efficiently.
problem Efficient computation of PKM inverse dynamics second derivatives.
method Recursive Lie-group formulation for serial robots adapted to PKM topology.
result Efficient computation of second time derivatives for PKM.
FlowChef steers RFMs to efficiently guide image generation tasks.
problem Efficiently guiding image generation tasks with RFMs.
method Developed a theoretical and empirical understanding of RFMs' vector field dynamics, proposing FlowChef for gradient-free navigation.
result FlowChef significantly outperforms baselines in performance, memory, and time requirements.
New pinching estimates control curvature ratios in inverse curvature flows.
problem Controlling curvature ratios in inverse curvature flows.
method Proving pinching estimates for strictly convex hypersurfaces in space forms.
result Smooth convergence of the inverse curvature flow is proven.
A neural network learns to control a two-link arm with non-linear dynamics.
problem Training spiking neural networks to control complex, non-linear systems.
method Feedback-based Online Local Learning Of Weights (FOLLOW) to train a network of spiking neurons with hidden layers.
result The network learns an inverse model of the arm's dynamics and uses it to generate a motor command for control.
Paper develops a framework for learning interpretable representations of sequential decision behavior.
problem Obtaining a transparent description of existing behavior.
method Inverse decision modeling framework, formalizing both forward and inverse problems.
result Learning interpretable representations of behavior, including suboptimal actions, biased beliefs, and imperfect knowledge.
Optimizes insurance pricing by accounting for policyholders' price sensitivity.
problem Traditional insurance pricing does not consider policyholders' price sensitivity.
method Formulates insurance pricing as a decision-making problem and uses off-policy evaluation and stochastic control.
result Neural networks outperform existing techniques for policy optimization.
New method identifies flawed internal models of the world in animals.
problem How animals make decisions with partial sensory information.
method Generalizes Inverse Rational Control to continuous nonlinear dynamics and noise.
result Identifies the best internal model explaining an agent's actions.
Efficiently designs distributed controllers for sparse systems with sub-linear sample complexity.
problem Designing robust distributed controllers for unknown-but-sparse linear systems.
method Combining distributed controller synthesis and structured linear inverse problems for system identification.
result Near-optimal distributed controllers can be learned with sub-linear sample complexity and near-linear time complexity.
AC-State discovers minimal latent state for control.
problem Discover minimal latent state from sensory information.
method Multi-step inverse model with information bottleneck.
result Guaranteed discovery of control-endogenous latent states.
Energy-based model learns cost functions from expert demonstrations for optimal control.
problem Learning unknown cost functions from expert demonstrations for optimal control.
method Maximum likelihood estimation via analysis by synthesis, combining Langevin dynamics with optimization and cooperative learning.
result The method can learn suitable cost functions for optimal control tasks.
IRL approach for studying consumer demand from observed behavior.
problem Confusing observational noise with consumer heterogeneity.
method Developed a Maximum Entropy IRL model for low-dimensional convex optimization.
result Observational noise can be mistaken for consumer heterogeneity.
New method infers human sensorimotor costs from behavior.
problem Inferring human sensorimotor costs from observed behavior.
method Inverse optimal control with signal-dependent noise.
result Recovering costs and benefits in sensorimotor behavior.
AIRL learns robust, generalizable reward functions from demonstrations.
problem Learning robust reward functions from demonstrations for changing environments.
method Adversarial Inverse Reinforcement Learning (AIRL) with hierarchical disentangled rewards.
result Generalizable policies and comparable results to state-of-the-art methods.
Tensor decomposition improves robot control by modeling inverse dynamics.
problem Accurate modeling of inverse dynamics for robot control.
method Tensor decomposition of sparse tensors to approximate non-linear functions.
result Superior performance compared to state-of-the-art methods.
This paper provides a full controlled version of algebraic K-theory. This includes a rich array of assembly maps; the controlled assembly isomorphism theorem identifying the controlled group with homology; and the stability theorem describing the behavior of the inverse limit as the control parameter goes to 0. There…
A new framework for controllable generation of discrete masked models.
problem Efficient controllable generation of discrete data models.
method Plug-and-play framework based on importance sampling.
result Demonstrates versatility across multiple domains, including protein design.
Geometric framework explains and controls implicit bias in machine learning.
problem Understanding and controlling the selection of solutions in overparameterized models.
method Developed a theoretical and constructive framework based on geometric corrections induced by gradient noise and continuous symmetries of the loss.
result Computed the induced bias across various architectures and enabled inverse design to shape the bias.
New approach transfers rewards learned in one environment to reinforcement learning in a new environment.
problem Transfer of rewards learned using inverse reinforcement learning from one environment to a new, different environment.
method Formulate the problem as a joint system of Bellman equations, develop minimax estimators for the target soft-q-function, solve the source and target system of equations jointly. result The coupled approach removes the first-order influence of source Bellman residual error compared to the sequential approach.
Optimal insurance minimizes ruin probability with non-decreasing functions.
problem Minimizing ruin probability with insurance premiums and non-decreasing functions.
method Reformulated problem with inverse survival function as control variable.
result Deductible insurance with maximum limit is optimal.
New method controls posterior collapse in VAEs with theoretical guarantees.
problem Posterior collapse in VAEs where encoder ignores latent structure.
method Inverse Lipschitz constraint on decoder network.
result Controls degree of posterior collapse for various VAE models.
The paper stabilizes invertible neural networks by using Gaussian mixture models.
problem Invertible neural networks can have exploding Lipschitz constants, leading to numerical errors.
method The authors use Gaussian mixture models to stabilize the latent distribution of invertible neural networks.
result Numerical simulations confirm that this modification improves sampling quality in multimodal applications.
Study on stability of mass theorems using inverse mean curvature flow.
problem Stability of Positive Mass Theorem and Riemannian Penrose Inequality.
method Uniform control of foliations by solutions to Inverse Mean Curvature Flow.
result Convergence of regions to flat or Schwarzschild metrics under specific conditions.
Paper proposes efficient image inversion and editing using rectified stochastic differential equations.
problem Inversion and editing of real images using generative models.
method Proposes RF inversion using dynamic optimal control and a linear quadratic regulator, extending to stochastic sampler for Flux.
result Allows state-of-the-art performance in zero-shot inversion and editing, outperforming prior works.
The paper analyzes reg-SGD for convex problems, proving convergence and quantifying the rate of convergence.
problem Minimizing convex, L-smooth functions in a Hilbert space.
method Regularized stochastic gradient descent with decaying regularization.
result Strong convergence to the minimum-norm solution without boundedness assumptions.
Study on stability of Positive Mass Theorem using Inverse Mean Curvature Flow.
problem Stability of Positive Mass Theorem in foliated regions with positive scalar curvature.
method Analyzes sequences of regions foliated by solutions to Inverse Mean Curvature Flow, focusing on convergence to flat annuli under specific conditions.
result Convergence of foliated regions to flat annuli under certain conditions, leading to stability of Positive Mass Theorem.
New method controls linear systems with adversarial disturbances.
problem Controlling linear dynamical systems under adversarial conditions.
method Novel convex relaxation using spectral filters from Hankel matrix eigenvectors.
result Polylogarithmic running time improvement over prior methods.
Improves deep learning performance on noisy datasets using inverse-variance weighting.
problem Heteroscedastic regression with varying noise levels.
method Batch Inverse-Variance (BIV) loss function for neural networks.
result Significantly improves network performance on noisy datasets compared to other methods.
The paper teaches robots to navigate by learning costs from expert demonstrations.
problem Teaching robots to navigate autonomously using only expert observations.
method Developed a map encoder and cost encoder to infer semantic class probabilities and a cost function from expert observations.
result Robots can learn to follow traffic rules in a simulator using only semantic observations.
Paper proposes a new framework for hypothesis testing in imaging.
problem Challenges in hypothesis testing for imaging data.
method Combines self-supervised imaging, vision-language models, and non-parametric hypothesis testing.
result Demonstrates improved power and robust error control in image-based phenotyping.
Study shows sample complexity for logistic regression with normal covariates.
problem Estimating parameters of logistic regression with normal design.
method Analyzes sample complexity in terms of dimension and inverse temperature.
result Shows two change-points in sample complexity curve based on inverse temperature.
The paper explores how ReLU DNNs can represent MPC policies and vice versa.
problem Representing MPC policies as ReLU DNNs and vice versa.
method Developed an approximate method for identifying input-space in ReLU nets resulting in PWA functions over polyhedral regions. Studied inverse multiparametric linear or quadratic programs for reconstruction of constraints and cost functions given a PWA function.
result Identification and representation of MPC policies as ReLU DNNs and vice versa.
Develops scalable differentiable physics for complex object interactions.
problem Limited scalability of existing differentiable physics solvers.
method Adopting meshes for arbitrary geometry, localized collision handling, and accelerated implicit differentiation.
result Significantly reduces memory and computation requirements compared to particle-based methods.
Improved flow-based inference speeds up and boosts accuracy for complex simulations.
problem Challenging inverse problems in astronomy, such as modeling strong gravitational lens systems.
method Refines flow-based generative models with simulator feedback for posterior inference.
result Improves accuracy by 53% and speeds up inference by up to 67x.
A paper uses RL to design microfluidic flow shapes efficiently.
problem Designing complex flow shapes in microfluidics using inverse problems.
method Formulated as a Reinforcement Learning (RL) problem, trained a DoubleDQN agent.
result Success frequency reached 90% in 200,000 episodes, rewards converged.
Study stability of mass theorems for hyperbolic manifolds foliated by IMCF.
problem Stability of Positive Mass Theorem and Riemannian Penrose Inequality in asymptotically hyperbolic manifolds.
method Sequence of regions foliated by IMCF, convergence to hyperbolic or AdS-Schwarzschild metrics.
result Convergence of regions to specific metrics under given conditions.
New IRL algorithm for continuous state spaces with formal guarantees.
problem Finding a reward function for expert behavior in continuous state spaces.
method Modeling the system using orthonormal functions and providing correctness proofs.
result Proof of correctness and formal guarantees on sample and time complexity.
Paper proposes a method to learn and exceed expert demonstrations in unknown reward environments.
problem Learning to outperform expert demonstrations in unknown reward environments.
method A novel concurrent reward and action policy learning approach with a stereo utility definition.
result The proposed method can outperform expert demonstrations in various environments.
Unified framework recovers exact input from SOM activation patterns.
problem Generating high-dimensional data from Self-Organizing Maps (SOMs).
method Inverting SOM activation patterns to recover input, using linear system and Tikhonov regularization.
result MUSIC framework produces coherent semantic transitions and maintains high classifier confidence.
Adapts VAEs for Bayesian inverse problems, quantifying uncertainty.
problem Bayesian inverse problems in scientific simulations.
method UQ-VAE: hybrid framework combining divergence-based variational inference and adjustable hyperparameters.
result Flexible, adaptive training of neural networks for posterior distribution.
WARPd method solves inverse problems with approximate sharpness conditions.
problem Reconstruction of signals from undersampled and noisy measurements.
method First-order method based on primal-dual iterations with restart-reweight scheme.
result WARPd achieves stable linear convergence under generic approximate sharpness condition.
Generative model creates frictional surfaces from friction laws.
problem Designing frictional interfaces with prescribed behavior is challenging.
method Uses Variational Autoencoders (VAEs) to infer surface topographies from friction laws.
result Efficiently generates candidate topographies without contact simulations.
CIR method preserves relation for case-control studies.
problem Learning low-dimensional structure in case-control studies.
method Contrastive inverse regression (CIR) on Stiefel manifold.
result CIR outperforms other methods for high-dimensional data.
A new method to understand neural networks by sampling the 'inverse set' of a neuron.
problem Understanding the internal representation of neurons in neural networks.
method Optimization-based sampling approach to characterize the input space that excites a neuron.
result Inspection of samples reveals regularities that help understand the neuron's representation.