Social distancing to combat the COVID-19 pandemic has led to widespread reductions in air pollutant emissions. Quantifying these changes requires a business-as-usual counterfactual that accounts for the synoptic and seasonal variability of air pollutants. We use a machine learning algorithm driven by information from the NASA GEOS-CF model to assess changes in nitrogen dioxide (NO.sub.2) and ozone (O.sub.3) at 5756 observation sites in 46 countries from January through June 2020. Reductions in NO.sub.2 coincide with the timing and intensity of COVID-19 restrictions, ranging from 60 % in severely affected cities (e.g., Wuhan, Milan) to little change (e.g., Rio de Janeiro, Taipei). On average, NO.sub.2 concentrations were 18 (13-23) % lower than business as usual from February 2020 onward. China experienced the earliest and steepest decline, but concentrations since April have mostly recovered and remained within 5 % of the business-as-usual estimate. NO.sub.2 reductions in Europe and the US have been more gradual, with a halting recovery starting in late March. We estimate that the global NO.sub.x (NO + NO.sub.2) emission reduction during the first 6 months of 2020 amounted to 3.1 (2.6-3.6) TgN, equivalent to 5.5 (4.7-6.4) % of the annual anthropogenic total. The response of surface O.sub.3 is complicated by competing influences of nonlinear atmospheric chemistry. While surface O.sub.3 increased by up to 50 % in some locations, we find the overall net impact on daily average O.sub.3 between February-June 2020 to be small. However, our analysis indicates a flattening of the O.sub.3 diurnal cycle with an increase in nighttime ozone due to reduced titration and a decrease in daytime ozone, reflecting a reduction in photochemical production.