The paper investigates how neural network weights evolve to monitor training progress.
problem Monitoring the training progress of neural networks in a cost-effective manner.
method Investigates the evolution of neural network weights in weight space.
result DNN models evolve on unique, smooth trajectories in weight space that can be used to track training progress.
Algorithm learns weight matrix from single trajectory of nonlinear dynamical system.
problem Learning weight matrix from a single trajectory of nonlinear dynamical system.
method Algorithm uses global stability and well-conditioned covariance to recover weight matrix.
result Algorithm recovers weight matrix with optimal sample complexity and linear running time.
Learning weights in a spiking neural network with hidden neurons, using local, stable and online rules, to control non-linear body dynamics is an open problem. Here, we employ a supervised scheme, Feedback-based Online Local Learning Of Weights (FOLLOW), to train a network of heterogeneous spiking neurons with hidden l…
New method recovers diverse policies from expert data using state-action pair weighting.
problem Recovering diverse policies from expert trajectories.
method Pointwise mutual information weighted behavioral cloning.
result Effective in focusing on state-action pairs most representative of the style.
Gradient flow with weight decay shows grokking effect in deep learning.
problem Understanding the grokking effect in deep learning.
method Analyzing gradient flow dynamics with weight decay.
result Weight decay causes slow norm reduction, explaining grokking.
We propose a new approach to the problem of neural network expressivity, which seeks to characterize how structural properties of a neural network family affect the functions it is able to compute. Our approach is based on an interrelated set of measures of expressivity, unified by the novel notion of trajectory length…
Proposes tracking DNN weights for uncertainty estimation.
problem Discarded information during DNN training.
method Tracks weights' trajectory during optimization.
result Competitive uncertainty estimation results.
This paper considers the growth in the length of one-dimensional trajectories as they are passed through deep ReLU neural networks, which, among other things, is one measure of the expressivity of deep networks. We generalise existing results, providing an alternative, simpler method for lower bounding expected traject…
Lo-Hp decouples weight generation into local and global policies to improve flexibility and efficiency.
problem Over-coupling and long-horizon issues in current optimization methods.
method Hybrid-Policy Sub-Trajectory Balance objective.
result Learning local optimization policies addresses long-horizon issues and enhances global weight generation.
Bayesian Neural ODEs improve vessel trajectory prediction with better uncertainty estimates.
problem Challenges in predicting vessel trajectories from irregular AIS data.
method Adopted a Gaussian process (GP) kernel-based prior on the vector field evaluated at measurement points, combined with probabilistic multiple shooting for long trajectories.
result Improved accuracy and uncertainty quantification in vessel trajectory predictions.
Improved motion prediction for self-driving cars using trajectory sets and auxiliary losses.
problem Accurately predicting future vehicle motion for self-driving cars.
method Classification over trajectory sets with an auxiliary loss for off-road predictions and spatial-temporal relationships.
result Significant improvement in motion prediction performance on small datasets using map information.
Develops anytime-valid stopping rules for SGD based on observed trajectory.
problem Stopping stochastic gradient descent (SGD) based on observed trajectory.
method Develops anytime-valid confidence sequences for stochastic gradient methods.
result Statistically valid, time-uniform stopping rules for SGD across convex and nonconvex settings.
The paper improves model-based reinforcement learning by using multi-timestep objectives.
problem Compounding errors in one-step dynamics models as trajectory length increases.
method Developed a multi-timestep objective as a weighted sum of losses at various future horizons.
result Exponentially decaying weights significantly improve long-horizon performance.
Algorithm learns stochastic system dynamics from data.
problem Recovering interpretable symbolic expressions for stochastic systems.
method Data-driven, trajectory averaging, drift-informed correction.
result Recover coefficients and densities to within 5% and 0.01 in total variation, respectively.
We present Memory Augmented Policy Optimization (MAPO), a simple and novel way to leverage a memory buffer of promising trajectories to reduce the variance of policy gradient estimate. MAPO is applicable to deterministic environments with discrete actions, such as structured prediction and combinatorial optimization ta…
The study analyzes optimization trajectories in neural networks to reveal redundancy and redundancy-reducing strategies.
problem Understanding the directional structure and redundancy in neural network optimization.
method Introducing natural notions of complexity for optimization trajectories and analyzing their directional nature.
result Training only scalar batchnorm parameters can match the performance of training the entire network, indicating potential for hybrid optimization schemes.
NDDV estimates data point value from a single stochastic trajectory.
problem Estimating marginal contributions of data points over stochastic training paths.
method Introduces Neural Dynamic Data Valuation (NDDV) using stochastic state and adjoint equations.
result NDDV provides a one-run, trajectory-conditioned estimator of data point value.
The study analyzes prediction errors in systems with memory kernels, providing bounds and stability results.
problem Prediction errors in stochastic dynamical systems with memory kernels.
method Analysis of generalized Langevin equations (GLEs) with Volterra equations, integrating synchronized noise coupling and weighted norms.
result Prediction discrepancies decay at a rate determined by the memory kernel's decay, quantitatively bounded by kernel estimation errors.
Learning and memory in the brain are implemented by complex, time-varying changes in neural circuitry. The computational rules according to which synaptic weights change over time are the subject of much research, and are not precisely understood. Until recently, limitations in experimental methods have made it challen…
Theoretical analysis of the error landscape of deep neural networks has garnered significant interest in recent years. In this work, we theoretically study the importance of noise in the trajectories of gradient descent towards optimal solutions in multi-layer neural networks. We show that adding noise (in different wa…
Novel method learns memory kernels in Langevin equations.
problem Estimating memory kernels in Langevin equations.
method Regularized Prony method for correlation functions, followed by regression over Sobolev norm-based loss function with RKHS regularization.
result Method outperforms other regression estimators in exponentially weighted L^2 space.
Proposes a model for generating survival trajectories and data.
problem Generating survival trajectories and data for new feature vectors.
method Autoencoder with specific structure, incorporating weighting scheme for robustness.
result Generates a prototype time-dependent trajectory for objects.
New method improves learning from multiple correlated data trajectories.
problem Learning from multiple correlated data trajectories without mixing assumptions.
method Hellinger localization framework for maximum likelihood estimation.
result Instance-optimal bounds that scale with full data budget under broad conditions.
New algorithm clusters trajectories from multiple Markov chains with near-optimal error.
problem Clustering trajectories from multiple unknown Markov chains.
method Two-stage algorithm: spectral clustering followed by likelihood-based refinement.
result Achieves near-optimal clustering error with high probability.
Paper examines adversarial attacks on weather forecasting models, focusing on TC trajectory prediction.
problem Adversarial attacks can mislead downstream TC trajectory predictions in DLWF models.
method Proposes Cyc-Attack, a method using a surrogate model and skewness-aware loss function to generate adversarial TC paths.
result Cyc-Attack achieves higher true positive rates and lower false alarm rates compared to conventional methods.
Disease progression models are instrumental in predicting individual-level health trajectories and understanding disease dynamics. Existing models are capable of providing either accurate predictions of patients prognoses or clinically interpretable representations of disease pathophysiology, but not both. In this pape…
Understanding how neural networks learn remains one of the central challenges in machine learning research. From random at the start of training, the weights of a neural network evolve in such a way as to be able to perform a variety of tasks, like classifying images. Here we study the emergence of structure in the wei…
Gradient descent with random weights in linear regression analyzed for various noise types.
problem Analyzing the impact of random noise on gradient descent in linear regression.
method Gradient descent with randomly weighted data points, various weighting distributions, geometric moment contraction.
result Characterization of implicit regularization and non-asymptotic convergence bounds.
DFR models dynamic distributional data with weighted Fréchet means.
problem Regression of distribution-valued responses over time.
method Dynamic Fréchet Regression (DFR) with index-aware weighting and feature selection.
result Improved predictive accuracy and feature recovery over existing methods.
Enhances RL by controlling policy stochasticity through trajectory entropy constraints.
problem Non-stationary Q-value estimation and short-sighted entropy tuning in maximum entropy RL.
method Proposes TECRL framework with separate Q-functions for reward and entropy, enforcing a trajectory entropy constraint.
result DSAC-E algorithm achieves higher returns and better stability on OpenAI Gym benchmarks.
Study non-parametric value function estimation from a single path.
problem Estimating value function from a single trajectory in Markov reward processes.
method Kernel-based multi-step temporal difference (TD) estimates, including K-step look-ahead TD and TD(λ). result Non-asymptotic guarantees for TD estimates, capturing interactions between mixing time and model mis-specification.
New analysis shows FM learns underlying dynamical structure, not just trajectory replay.
problem Understanding whether flow matching models learn transferable dynamical structure or merely replay trajectories.
method Derived velocity field implied by FM objective, characterized as a continuous-time dynamical system.
result FM models can be seen as parametric surrogates of nonparametric solutions, providing strong probabilistic forecasts.
Proposes a new method for dynamic treatment regimes that improves sample efficiency and stability.
problem Challenges in estimating optimal treatments for individuals with dynamic decision-making stages.
method Focuses on prioritizing alignment between observed and optimal treatment trajectories across decision stages.
result Improves sample efficiency and stability of IPWE-based methods by relaxing the alignment requirement.
Unified view on selective credit assignment for reinforcement learning.
problem Efficient credit assignment in reinforcement learning.
method Unified temporal-difference algorithms with selective weightings.
result New algorithms for backward credit assignment and off-policy learning.
Averaging recent model checkpoints speeds up training time.
problem Training large vision or language models is time-consuming.
method Average the weights of the k latest checkpoints.
result Speeds up training by dozens of epochs, saving up to 68 GPU hours.
New metric shows how different regularization methods affect deep linear networks.
problem Understanding the training dynamics of deep linear networks.
method Introduced a new metric called layer imbalance to analyze training dynamics. Demonstrated behavior of different regularization methods and stochastic gradient descent.
result Different regularization methods behave similarly, leading to a flat minima.
Proposes SSC for estimating counterfactual survival trajectories from observational data.
problem Challenges in estimating causal effects on time-to-event outcomes from observational data.
method Synthetic Survival Control (SSC) framework for estimating counterfactual hazard trajectories in panel data settings.
result SSC estimates counterfactual hazard trajectories as a weighted combination of observed trajectories from other units.
RWR converges to global optimum in certain settings.
problem Proving convergence of RWR to optimal policy.
method Iterative learning with return-weighted log-likelihood.
result RWR converges to global optimum under certain conditions.
New method improves deep RL by combining emphatic weightings with replay data.
problem Improving sample efficiency and scaling model-free RL methods.
method Developed a multi-step emphatic weighting and time-reversed n-step TD learning algorithm. result The new approach reduces variance and provides convergence guarantees.
Estimates network structure and interaction rules from multiple agent trajectories.
problem Modeling multi-agent systems on networks from data.
method Jointly infers network topology and interaction kernels using non-convex optimization.
result ORALS estimator is consistent and asymptotically normal under coercivity conditions.
Paper defines a new distance metric for comparing learning tasks.
problem Comparing difficulty of learning tasks between source and target.
method Information geometry, optimal transport, coupled transfer distance.
result Coupled transfer distance correlates with fine-tuning difficulty.
TSC improves causal effect estimation in panel data.
problem Estimating causal effects in panel data with a single treated unit.
method Targeted synthetic control method that refines initial weights through a one-dimensional targeted update.
result TSC consistently improves estimation accuracy over state-of-the-art SCM baselines.
Study supports recovery of PDEs from noisy data using a specific regularization method.
problem Support recovery of PDEs from a single noisy trajectory.
method Applying ℓ1-regularized Pseudo-Least Squares model to a given data set.
result Support of ℓ1-c coefficients asymptotically converges to the true signed-support of the PDE.
Enhanced Neural ODEs outperform traditional models in image classification and video prediction.
problem Efficiently modeling time-varying dynamics in neural networks.
method Proposed a novel family of non-autonomous Neural ODEs with time-varying weights.
result Outperformed previous Neural ODE variants in speed and representational capacity.
New model predicts stock performance in large equity markets.
problem Predicting stock performance in large equity markets over long time horizons.
method Rank-based volatility stabilized models calibrated to empirical data.
result The model exhibits relative arbitrage and statistically fits empirical features.
Diagonal linear networks converge to lasso regularization path during training.
problem Understanding the regularization behavior of diagonal linear networks.
method Analyzing the training trajectory of diagonal linear networks and comparing it to the lasso regularization path.
result The training trajectory of diagonal linear networks is closely related to the lasso regularization path.
VLBM learns MDP transitions from limited data, improving OPE performance.
problem Limited coverage of state and action space in offline trajectories.
method VLBM uses variational inference with RSA and branching architecture.
result VLBM outperforms existing OPE methods on deep OPE benchmark.
This paper proposes recurrent neuron networks (RNNs) for a fingerprinting indoor localization using WiFi. Instead of locating user's position one at a time as in the cases of conventional algorithms, our RNN solution aims at trajectory positioning and takes into account the relation among the received signal strength i…