Matias D. Cattaneo

Matias D. Cattaneo, Jason M. Klusowski, Boris Shigida

In previous literature, backward error analysis was used to find ordinary differential equations (ODEs) approximating the gradient descent trajectory. It was found that finite step sizes implicitly regularize solutions because terms appearing in the ODEs penalize the two-norm of the loss gradients. We prove that the existence of similar implicit regularization in RMSProp and Adam depends on their hyperparameters and the training stage, but with a different "norm" involved: the corresponding ODE terms either penalize the (perturbed) one-norm of the loss gradients or, conversely, impede its reduction (the latter case being typical). We also conduct numerical experiments and discuss how the proven facts can influence generalization.

Matias D. Cattaneo, Jason M. Klusowski, Peter M. Tian

Decision tree learning is increasingly being used for pointwise inference. Important applications include causal heterogenous treatment effects and dynamic policy decisions, as well as conditional quantile regression and design of experiments, where tree estimation and inference is conducted at specific values of the covariates. In this paper, we call into question the use of decision trees (trained by adaptive recursive partitioning) for such purposes by demonstrating that they can fail to achieve polynomial rates of convergence in uniform norm with non-vanishing probability, even with pruning. Instead, the convergence may be arbitrarily slow or, in some important special cases, such as honest regression trees, fail completely. We show that random forests can remedy the situation, turning poor performing trees into nearly optimal procedures, at the cost of losing interpretability and introducing two additional tuning parameters. The two hallmarks of random forests, subsampling and the random feature selection mechanism, are seen to each distinctively contribute to achieving nearly optimal performance for the model class considered.

Matias D. Cattaneo, Boris Shigida

With limited high-quality data and growing compute, multi-epoch training is gaining back its importance across sub-areas of deep learning. Adam(W), versions of which are go-to optimizers for many tasks such as next token prediction, has two momentum hyperparameters $(β_1, β_2)$ controlling memory and one very important hyperparameter, batch size, controlling (in particular) the amount mini-batch noise. We introduce a theoretical framework to understand how mini-batch noise influences the implicit bias of memory in Adam (depending on $β_1$, $β_2$) towards sharper or flatter regions of the loss landscape, which is commonly observed to correlate with the generalization gap in multi-epoch training. We find that in the case of large batch sizes, higher $β_2$ increases the magnitude of anti-regularization by memory (hurting generalization), but as the batch size becomes smaller, the dependence of (anti-)regulariation on $β_2$ is reversed. A similar monotonicity shift (in the opposite direction) happens in $β_1$. In particular, the commonly "default" pair $(β_1, β_2) = (0.9, 0.999)$ is a good choice if batches are small; for larger batches, in many settings moving $β_1$ closer to $β_2$ is much better in terms of validation accuracy in multi-epoch training. Moreover, our theoretical derivations connect the scale of the batch size at which the shift happens to the scale of the critical batch size. We illustrate this effect in experiments with small-scale data in the about-to-overfit regime.

Matias D. Cattaneo, Boris Shigida

In modern optimization methods used in deep learning, each update depends on the history of previous iterations, often referred to as memory, and this dependence decays fast as the iterates go further into the past. For example, gradient descent with momentum has exponentially decaying memory through exponentially averaged past gradients. We introduce a general technique for identifying a memoryless algorithm that approximates an optimization algorithm with memory. It is obtained by replacing all past iterates in the update by the current one, and then adding a correction term arising from memory (also a function of the current iterate). This correction term can be interpreted as a perturbation of the loss, and the nature of this perturbation can inform how memory implicitly (anti-)regularizes the optimization dynamics. As an application of our theory, we find that Lion does not have the kind of implicit anti-regularization induced by memory that AdamW does, providing a theory-based explanation for Lion's better generalization performance recently documented.

Matias D. Cattaneo, Richard K. Crump, Max H. Farrell et al.

Binscatter is a popular method for visualizing bivariate relationships and conducting informal specification testing. We study the properties of this method formally and develop enhanced visualization and econometric binscatter tools. These include estimating conditional means with optimal binning and quantifying uncertainty. We also highlight a methodological problem related to covariate adjustment that can yield incorrect conclusions. We revisit two applications using our methodology and find substantially different results relative to those obtained using prior informal binscatter methods. General purpose software in Python, R, and Stata is provided. Our technical work is of independent interest for the nonparametric partition-based estimation literature.