Hikaru Saijo

Macroeconomist at UC Santa Cruz, カリフォルニア大学サンタクルーズ校経済学部

[Hikaru Saijo @hpfilter]

@xajpdtpjunpad 僕もたまたま昨日の授業で教えました（笑）
なるほど、cross-sectionalなevidenceだけだとるさんの言う可能性は排除できないですね。
でも線形モデルだとそのままextrapolateしてしまって政策効果を過大評価してしまう、というinsightは面白いなと思いました。

[Hikaru Saijo @hpfilter]

@xajpdtpjunpad この論文とか見ると所得、流動性によってMPCは結構異質に出ています
https://t.co/BBU6o6Ja5I

[Hikaru Saijo @hpfilter]

Bring back the math SAT to UC admissions! I signed the letter. If you are a UC faculty, please consider signing.

[Neetu Arnold @neetu_arnold]

University of California STEM professors want standardized tests back due to severe math deficiencies among students:

“We now observe preparation gaps so severe that instructors must reteach middle school mathematics”

“The current admissions metric, based primarily on GPA & essays, can no longer reliably distinguish readiness for university-level STEM majors in an era of severe grade inflation & AI assisted application essays”

[Hikaru Saijo @hpfilter]

@cmatthes_econ This makes me pessimistic on two fronts. 1) Obviously, models are getting scary good and 2) Are labs going to be making most scientific progress while normal academics only have access to models that are say 6mo-1year behind the frontier??

[Hikaru Saijo @hpfilter]

@matthenryyoung I don't know James but no, economists don't copy and paste citation lists

[Hikaru Saijo @hpfilter]

@aledinola But you need to check if they solved it correctly, and AI will write you the dynare mod file so the verification will be cheap!

[Hikaru Saijo @hpfilter]

Some used to give Dynare a bad rap for enabling DSGE-slop (not my view), but it was an important verification engine (and symbolic!) even in the pre-LLM era. Now that we’re speed running macro research with AI agents, I think it’ll become more and more important.

[Emily Oster @ProfEmilyOster]

Advice for PhD students in economics about using AI, from the brilliant Isaiah Andrews. This should probably be circulated to all PhD cohorts

https://t.co/07xEbmx5n5

[Hikaru Saijo @hpfilter]

@MahdiKahou I am a big fan of your ML blog posts. Hope you'll find some time soon to update these!

[Hikaru Saijo @hpfilter]

I was teaching this plot of a correlation of life satisfaction vs GDP in an undergrad macroeconomics class today (yes cardinal utility blah blah), and out of curiosity I asked students to rate their own life satisfaction. To my pleasant surprise, most students rated 8 to 10 range. The kids are alright!

[Hikaru Saijo @hpfilter]

@lucasian76 I think the rule of thumb is you increase the number of layers until the test errors stop decreasing. Unfortunately I found no good intuition for which activation function to use, although I found LeakyReLu or Tanh tends to perform reasonably well for econ applocations

[Hikaru Saijo @hpfilter]

@xajpdtpjunpad あとVS codeにはtex extension（tex workshop）もあるので、ドラフトもClaudeにコードを参照してもらったりして書いてもらうこともできます。ここまで来るともはや自分の存在意義が分からなくなりますが（笑）

[Hikaru Saijo @hpfilter]

@xajpdtpjunpad 僕はVS codeにClaude code extensionを入れて作業してるのですが、これだと結構スムーズに文脈伝えられる気がします。Cursorは使ったことないので分からないですが。

[Ben Moll @ben_moll]

Every journal editor should read this:

https://t.co/cGstyJOa3m

[Hikaru Saijo @hpfilter]

@t_holden That I don’t know. Never tried git:)

[Hikaru Saijo @hpfilter]

Yes thank you

[Jesús Fernández-Villaverde @JesusFerna7026]

Saturday, I gave a talk at ASSA 2026 on my new paper ``Macroeconomic Effects of Production Networks: A Deep Learning Approach,’’ with @cmatthes_econ, @hpfilter, and @MacroInPieces.

Several attendees asked for a copy of the slides I used (sorry, we are still a few weeks away from circulating a completed draft), so I am linking them here:

https://t.co/bQZq7T0XMe

There has been a lively debate over the last few weeks on X about what deep learning can do in macro. I think this is a good example of what we can now study.

Dynamic stochastic models with non-trivial input-output structures are a beast to compute. They are inherently nonlinear, and you need to carry not only aggregate state variables but also all the sector-specific variables, such as sectoral productivity and sector-specific capital. If you have, as we do in the paper’s calibration to match U.S. input-output tables, 37 sectors, you end up with at least 74 state variables. Even very aggressive sparse-grid allocations, such as Smolyak, will struggle with that.

A deep neural network can deal with this problem, especially if you build it using the symmetry (or, if you prefer, exchangeability) ideas I discuss here:

https://t.co/Uv33AbaTlo

with @MahdiKahou, @jlperla, and Arnav Sood.

We also show that adopting a deep learning approach changes the answers you get relative to more traditional solution methods. More concretely, we capture endogenous changes in relative prices across sectors that perturbation solutions largely miss. That leads to materially different elasticities of output, investment, and labor supply to sectoral shocks.

In our benchmark calibration, we find substantial attenuation of sectoral shocks, precisely because of these relative price changes. When steel becomes too expensive following a productivity shock in the steel industry, car manufacturers switch to more plastic.

This result resonates with my own earlier work on the macroeconomics of wars. One lesson from wars over the last 120 years is how resilient modern economies have been to large disruptions from mobilization, blockades, or bombing. What looked like bottlenecks that would stop production turned out to be inconveniences, because there are many ways to produce a tank or an airplane. Some alternatives were less efficient than the optimal one, but the productivity losses were not as large as pre-war planners envisioned when they took a static view of resource allocation.

Our results replicate that intuition inside a standard stochastic multi-sector business cycle model.

Of course, we could throw wrenches into the economy’s reallocation process, but, at this moment, I think the insight is robust.

[Hikaru Saijo @hpfilter]

@xajpdtpjunpad 単に鍵付きの人をブロックしているだけでは？僕の憶測ですが。